Added convert to static [u8]

.github/FUNDING.yml

@@ -1,12 +0,0 @@
-# These are supported funding model platforms
-
-github: fulmicoton
-patreon: # Replace with a single Patreon username
-open_collective: # Replace with a single Open Collective username
-ko_fi: # Replace with a single Ko-fi username
-tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
-community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
-liberapay: # Replace with a single Liberapay username
-issuehunt: # Replace with a single IssueHunt username
-otechie: # Replace with a single Otechie username
-custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/ISSUE_TEMPLATE/actions.md

@@ -1,13 +0,0 @@
----
-name: Actions
-about: Actions not directly related to producing code.
-
----
-
-# Actions title
-
-Action description. 
-e.g. 
-- benchmark
-- investigate and report
-- etc.

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,19 +0,0 @@
----
-name: Bug report
-about: Create a report to help us improve
-
----
-
-**Describe the bug**
-- What did you do?
-- What happened?
-- What was expected?
-
-**Which version of tantivy are you using?**
-If "master",  ideally give the specific sha1 revision.
-
-**To Reproduce**
-
-If your bug is deterministic, can you give a minimal reproducing code?
-Some bugs are not deterministic. Can you describe with precision in which context it happened?
-If this is possible, can you share your code?

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,14 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**[Optional] describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.

.github/ISSUE_TEMPLATE/question.md

@@ -1,7 +0,0 @@
----
-name: Question
-about: Ask any question about tantivy's usage...
-
----
-
-Try to be specific about your use case...

.github/dependabot.yml

@@ -1,8 +0,0 @@
-version: 2
-updates:
-- package-ecosystem: cargo
-  directory: "/"
-  schedule:
-    interval: daily
-    time: "20:00"
-  open-pull-requests-limit: 10

.github/workflows/coverage.yml

@@ -1,27 +0,0 @@
-name:                           coverage
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
-jobs:
-  test:
-    name:                       coverage
-    runs-on:                    ubuntu-latest
-    container:
-      image:                    xd009642/tarpaulin:develop-nightly
-      options:                  --security-opt seccomp=unconfined
-    steps:
-      - name:                   Checkout repository
-        uses:                   actions/checkout@v2
-
-      - name:                   Generate code coverage
-        run: |
-          cargo +nightly tarpaulin --verbose --all-features --workspace --timeout 120 --out Xml
-
-      - name:                   Upload to codecov.io
-        uses:                   codecov/codecov-action@v1
-        with:
-          # token:                ${{secrets.CODECOV_TOKEN}} # not required for public repos
-          fail_ci_if_error:     true

.github/workflows/test.yml

@@ -1,30 +0,0 @@
-name: Rust
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
-
-env:
-  CARGO_TERM_COLOR: always
-
-jobs:
-  build:
-
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v2
-    - name: Build
-      run: cargo build --verbose --workspace
-    - name: Install latest nightly to test also against unstable feature flag
-      uses: actions-rs/toolchain@v1
-      with:
-            toolchain: nightly
-            override: true
-            components: rustfmt
-    - name: Run tests
-      run: cargo test --all-features --verbose --workspace
-    - name: Check Formatting
-      run: cargo fmt --all -- --check

.gitignore

@@ -1,5 +1,3 @@
-tantivy.iml
-proptest-regressions
 *.swp
 target
 target/debug
@@ -12,4 +10,3 @@ cpp/simdcomp/bitpackingbenchmark
 *.bk
 .idea
 trace.dat
-cargo-timing*

.travis.yml

@@ -1,17 +1,14 @@
-# Based on the "trust" template v0.1.2
-# https://github.com/japaric/trust/tree/v0.1.2
-
-dist: trusty
 language: rust
-services: docker
 sudo: required
-
+cache: cargo
+rust:
+  - nightly
 env:
   global:
-    - CRATE_NAME=tantivy
+    - CC=gcc-4.8
+    - CXX=g++-4.8
     - TRAVIS_CARGO_NIGHTLY_FEATURE=""
-    # - secure: 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
-
+    - secure: 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
 addons:
   apt:
     sources:
@@ -25,68 +22,16 @@ addons:
       - libdw-dev
       - binutils-dev
       - cmake
-
-matrix:
-  include:
-    # Android
-    - env: TARGET=aarch64-linux-android DISABLE_TESTS=1
-    #- env: TARGET=arm-linux-androideabi DISABLE_TESTS=1
-    #- env: TARGET=armv7-linux-androideabi DISABLE_TESTS=1
-    #- env: TARGET=i686-linux-android DISABLE_TESTS=1
-    #- env: TARGET=x86_64-linux-android DISABLE_TESTS=1
-
-    # Linux
-    #- env: TARGET=aarch64-unknown-linux-gnu
-    #- env: TARGET=i686-unknown-linux-gnu
-    - env: TARGET=x86_64-unknown-linux-gnu CODECOV=1 #UPLOAD_DOCS=1
-    # - env: TARGET=x86_64-unknown-linux-musl CODECOV=1
-    # OSX
-    #- env: TARGET=x86_64-apple-darwin
-    #  os: osx
-
-before_install:
-  - set -e
-  - rustup self update
-  - rustup component add rustfmt
-
-install:
-  - sh ci/install.sh
-  - source ~/.cargo/env || true
-  - env | grep "TRAVIS"
-
 before_script:
   - export PATH=$HOME/.cargo/bin:$PATH
   - cargo install cargo-update || echo "cargo-update already installed"
   - cargo install cargo-travis || echo "cargo-travis already installed"
-
 script:
-  - bash ci/script.sh
-  - cargo fmt --all -- --check
-
-before_deploy:
-  - sh ci/before_deploy.sh
-
+  - cargo build
+  - cargo test
+  - cargo test -- --ignored
+  - cargo run --example simple_search
+  - cargo doc
 after_success:
-  # Needs GH_TOKEN env var to be set in travis settings
-  - if [[ -v GH_TOKEN ]]; then echo "GH TOKEN IS SET"; else echo "GH TOKEN NOT SET"; fi
-  - if [[ -v UPLOAD_DOCS ]]; then cargo doc; cargo doc-upload; else echo "doc upload disabled."; fi
-
-#cache: cargo
-#before_cache:
-#  # Travis can't cache files that are not readable by "others"
-#  - chmod -R a+r $HOME/.cargo
-#  - find ./target/debug -type f -maxdepth 1 -delete
-#  - rm -f  ./target/.rustc_info.json
-#  - rm -fr ./target/debug/{deps,.fingerprint}/tantivy*
-#  - rm -r target/debug/examples/
-#  - ls -1 examples/ | sed -e 's/\.rs$//' | xargs -I "{}" find target/* -name "*{}*" -type f -delete
-
-#branches:
-#  only:
-#    # release tags
-#    - /^v\d+\.\d+\.\d+.*$/
-#    - master
-
-notifications:
-  email:
-    on_success: never
+  - cargo coveralls --exclude-pattern src/functional_test.rs
+  - cargo doc-upload

ARCHITECTURE.md

@@ -1,295 +0,0 @@
-# Tantivy
-
-## What is tantivy?
-
-Tantivy is a library that is meant to build search engines. Although it is by no means a port of Lucene, its architecture is strongly inspired by it. If you are familiar with Lucene, you may be struck by the overlapping vocabulary.
-This is not fortuitous.
-
-Tantivy's bread and butter is to address the problem of full-text search :
-
-Given a large set of textual documents, and a text query, return the K-most relevant documents in a very efficient way. To execute these queries rapidly, the tantivy needs to build an index beforehand. The relevance score implemented in the tantivy is not configurable. Tantivy uses the same score as the default similarity used in Lucene / Elasticsearch, called [BM25](https://en.wikipedia.org/wiki/Okapi_BM25).
-
-But tantivy's scope does not stop there. Numerous features are required to power rich-search applications. For instance, one may want to:
-- compute the count of documents matching a query in the different section of an e-commerce website,
-- display an average price per meter square for a real estate search engine,
-- take into account historical user data to rank documents in a specific way,
-- or even use tantivy to power an OLAP database.
-
-A more abstract description of the problem space tantivy is trying to address is the following.
-
-Ingest a large set of documents, create an index that makes it possible to
-rapidly select all documents matching a given predicate (also known as a query) and
-collect some information about them ([See collector](#collector-define-what-to-do-with-matched-documents)).
-
-Roughly speaking the design is following these guiding principles:
-- Search should be O(1) in memory.
-- Indexing should be O(1) in memory. (In practice it is just sublinear)
-- Search should be as fast as possible
-
-This comes at the cost of the dynamicity of the index: while it is possible to add, and delete documents from our corpus, the tantivy is designed to handle these updates in large batches.
-
-## [core/](src/core): Index, segments, searchers.
-
-Core contains all of the high-level code to make it possible to create an index, add documents, delete documents and commit.
-
-This is both the most high-level part of tantivy, the least performance-sensitive one, the seemingly most mundane code... And paradoxically the most complicated part.
-
-### Index and Segments...
-
-A tantivy index is a collection of smaller independent immutable segments. 
-Each segment contains its own independent set of data structures.
-
-A segment is identified by a segment id that is in fact a UUID.
-The file of a segment has the format
-
- ```segment-id . ext ```
-
-The extension signals which data structure (or [`SegmentComponent`](src/core/segment_component.rs)) is stored in the file.
-
-A small `meta.json` file is in charge of keeping track of the list of segments, as well as the schema.
-
-On commit, one segment per indexing thread is written to disk, and the `meta.json` is then updated atomically.
-
-For a better idea of how indexing works, you may read the [following blog post](https://fulmicoton.com/posts/behold-tantivy-part2/).
-
-
-### Deletes
-
-Deletes happen by deleting a "term". Tantivy does not offer any notion of primary id, so it is up to the user to use a field in their schema as if it was a primary id, and delete the associated term if they want to delete only one specific document.
-
-On commit, tantivy will find all of the segments with documents matching this existing term and create a [tombstone file](src/fastfield/delete.rs) that represents the bitset of the document that are deleted.
-Like all segment files, this file is immutable. Because it is possible to have more than one tombstone file at a given instant, the tombstone filename has the format ``` segment_id . commit_opstamp . del```.
-
-An opstamp is simply an incremental id that identifies any operation applied to the index. For instance, performing a commit or adding a document.
-
-
-### DocId
-
-Within a segment, all documents are identified by a DocId that ranges within `[0, max_doc)`.
-where `max_doc` is the number of documents in the segment, (deleted or not). Having such a compact `DocId` space is key to the compression of our data structures.
-
-The DocIds are simply allocated in the order documents are added to the index.
-
-### Merges
-
-In separate threads, tantivy's index writer search for opportunities to merge segments.
-The point of segment merge is to:
-- eventually get rid of tombstoned documents
-- reduce the otherwise ever-growing number of segments.
-
-Indeed, while having several segments instead of one does not hurt search too much, having hundreds can have a measurable impact on the search performance.
-
-### Searcher
-
-The user of the library usually does not need to know about the existence of Segments.
-Searching is done through an object called a [`Searcher`](src/core/searcher.rs), that captures a
-snapshot of the index at one point of time, by holding a list of [SegmentReader](src/core/segment_reader.rs).
-
-In other words, regardless of commits, file garbage collection, or segment merge that might happen, as long as the user holds and reuse the same [Searcher](src/core/searcher.rs), search will happen on an immutable snapshot of the index.
-
-## [directory/](src/directory): Where should the data be stored?
-
-Tantivy, like Lucene, abstracts the place where the data should be stored in a key-trait
-called [`Directory`](src/directory/directory.rs).
-Contrary to Lucene however, "files" are quite different from some kind of `io::Read` object.
-Check out [`src/directory/directory.rs`](src/directory/directory.rs) trait for more details.
-
-Tantivy ships two main directory implementation: the `MMapDirectory` and the `RAMDirectory`,
-but users can extend tantivy with their own implementation.
-
-## [schema/](src/schema): What are documents?
-
-Tantivy's document follows a very strict schema, decided before building any index.
-
-The schema defines all of the fields that the indexes [`Document`](src/schema/document.rs) may and should contain, their types (`text`, `i64`, `u64`, `Date`, ...) as well as how it should be indexed / represented in tantivy.
-
-Depending on the type of the field, you can decide to
-- put it in the docstore
-- store it as a fast field
-- index it
-
-Practically, tantivy will push values associated with this type to up to 3 respective
-data structures.
-
-*Limitations*
-
-As of today, tantivy's schema imposes a 1:1 relationship between a field that is being ingested and a field represented in the search index. In sophisticated search application, it is fairly common to want to index a field twice using different tokenizers, or to index the concatenation of several fields together into one field.
-
-This is not something tantivy supports, and it is up to the user to duplicate field / concatenate fields before feeding them to tantivy.
-
-## General information about these data structures.
-
-All data structures in tantivy, have:
-- a writer
-- a serializer
-- a reader
-
-The writer builds an in-memory representation of a batch of documents. This representation is not searchable. It is just meant as an intermediary mutable representation, to which we can sequentially add
-the document of a batch. At the end of the batch (or if a memory limit is reached), this representation
-is then converted into an on-disk immutable representation, that is extremely compact.
-This conversion is done by the serializer.
-
-Finally, the reader is in charge of offering an API to read on this on-disk read-only representation.
-In tantivy, readers are designed to require very little anonymous memory. The data is read straight from an mmapped file, and loading an index is as fast as mmapping its files.
-
-## [store/](src/store): Here is my DocId, Gimme my document!
-
-The docstore is a row-oriented storage that, for each document, stores a subset of the fields
-that are marked as stored in the schema. The docstore is compressed using a general-purpose algorithm
-like LZ4.
-
-**Useful for**
-
-In search engines, it is often used to display search results.
-Once the top 10 documents have been identified, we fetch them from the store, and display them or their snippet on the search result page (aka SERP).
-
-**Not useful for**
-
-Fetching a document from the store is typically a "slow" operation. It usually consists in
-- searching into a compact tree-like data structure to find the position of the right block.
-- decompressing a small block
-- returning the document from this block.
-
-It is NOT meant to be called for every document matching a query.
-
-As a rule of thumb, if you hit the docstore more than 100 times per search query, you are probably misusing tantivy.
-
-
-## [fastfield/](src/fastfield): Here is my DocId, Gimme my value!
-
-Fast fields are stored in a column-oriented storage that allows for random access.
-The only compression applied is bitpacking. The column comes with two meta data.
-The minimum value in the column and the number of bits per doc.
-
-Fetching a value for a `DocId` is then as simple as computing
-
-```
-min_value + fetch_bits(num_bits * doc_id..num_bits * (doc_id+1))
-```
-
-This operation just requires one memory fetch.
-Because, DocSets are scanned through in order (DocId are iterated in a sorted manner) which
-also help locality.
-
-In Lucene's jargon, fast fields are called DocValues.
-
-**Useful for**
-
-They are typically integer values that are useful to either rank or compute aggregate over
-all of the documents matching a query (aka [DocSet](src/docset.rs)).
-
-For instance, one could define a function to combine upvotes with tantivy's internal relevancy score.
-This can be done by fetching a fast field during scoring.
-One could also compute the mean price of the items matching a query in an e-commerce website.
-This can be done by fetching a fast field in a collector.
-Finally one could decide to post-filter a docset to remove docset with a price within a specific range.
-If the ratio of filtered out documents is not too low, an efficient way to do this is to fetch the price and apply the filter on the collector side.
-
-Aside from integer values, it is also possible to store an actual byte payload.
-For advanced search engine, it is possible to store all of the features required for learning-to-rank in a byte payload, access it during search, and apply the learning-to-rank model.
-
-Finally facets are a specific kind of fast field, and the associated source code is in [`fastfield/facet_reader.rs`](src/fastfield/facet_reader.rs).
-
-# The inverted search index.
-
-The inverted index is the core part of full-text search.
-When presented a new document with the text field "Hello, happy tax payer!", tantivy breaks it into a list of so-called tokens. In addition to just splitting these strings into tokens, it might also do different kinds of operations like dropping the punctuation, converting the character to lowercase, apply stemming, etc. Tantivy makes it possible to configure the operations to be applied in the schema (tokenizer/ is the place where these operations are implemented).
-
-For instance, the default tokenizer of tantivy would break our text into: `[hello, happy, tax, payer]`.
-The document will therefore be registered in the inverted index as containing the terms
-`[text:hello, text:happy, text:tax, text:payer]`.
-
-The role of the inverted index is, when given a term, gives us in return a very fast iterator over the sorted doc ids that match the term.
-
-Such an iterator is called a posting list. In addition to giving us `DocId`, they can also give us optionally the number of occurrence of the term for each document, also called term frequency or TF.
-
-These iterators being sorted by DocId, one can create an iterator over the document containing `text:tax AND text:payer`, `(text:tax AND text:payer) OR (text:contribuable)` or any boolean expression.
-
-In order to represent the function
-```Term ⟶ Posting```
-
-The inverted index actually consists of two data structures chained together.
-
-- [Term](src/schema/term.rs) ⟶ [TermInfo](src/postings/term_info.rs) is addressed by the term dictionary.
-- [TermInfo](src/postings/term_info.rs) ⟶ [Posting](src/postings/postings.rs) is addressed by the posting lists.
-
-Where [TermInfo](src/postings/term_info.rs) is an object containing some meta data about a term.
-
-
-## [termdict/](src/termdict): Here is a term, give me the [TermInfo](src/postings/term_info.rs)!
-
-Tantivy's term dictionary is mainly in charge of supplying the function
-
-[Term](src/schema/term.rs) ⟶ [TermInfo](src/postings/term_info.rs)
-
-It is itself broken into two parts.
-- [Term](src/schema/term.rs) ⟶ [TermOrdinal](src/termdict/mod.rs) is addressed by a finite state transducer, implemented by the fst crate.
-- [TermOrdinal](src/termdict/mod.rs) ⟶ [TermInfo](src/postings/term_info.rs) is addressed by the term info store.
-
-
-## [postings/](src/postings): Iterate over documents... very fast!
-
-A posting list makes it possible to store a sorted list of doc ids and for each doc store
-a term frequency as well.
-
-The posting lists are stored in a separate file. The [TermInfo](src/postings/term_info.rs) contains an offset into that file and a number of documents for the given posting list. Both are required and sufficient to read the posting list.
-
-The posting list is organized in block of 128 documents.
-One block of doc ids is followed by one block of term frequencies.
-
-The doc ids are delta encoded and bitpacked.
-The term frequencies are bitpacked.
-
-Because the number of docs is rarely a multiple of 128, the last block may contain an arbitrary number of docs between 1 and 127 documents. We then use variable int encoding instead of bitpacking.
-
-## [positions/](src/positions): Where are my terms within the documents?
-
-Phrase queries make it possible to search for documents containing a specific sequence of terms.
-For instance, when the phrase query "the art of war" does not match "the war of art".
-To make it possible, it is possible to specify in the schema that a field should store positions in addition to being indexed.
-
-The token positions of all of the terms are then stored in a separate file with the extension `.pos`.
-The [TermInfo](src/postings/term_info.rs) gives an offset (expressed in position this time) in this file. As we iterate throught the docset,
-we advance the position reader by the number of term frequencies of the current document.
-
-## [fieldnorms/](src/fieldnorms): Here is my doc, how many tokens in this field?
-
-The [BM25](https://en.wikipedia.org/wiki/Okapi_BM25) formula also requires to know the number of tokens stored in a specific field for a given document. We store this information on one byte per document in the fieldnorm.
-The fieldnorm is therefore compressed. Values up to 40 are encoded unchanged.
-
-
-## [tokenizer/](src/tokenizer): How should we process text?
-
-Text processing is key to a good search experience.
-Splits or normalize your text too much, and the search results will have a less precision and a higher recall.
-Do not normalize, or under split your text, you will end up with a higher precision and a lesser recall.
-
-Text processing can be configured by selecting an off-the-shelf [`Tokenizer`](./src/tokenizer/tokenizer.rs) or implementing your own to first split the text into tokens, and then chain different [`TokenFilter`](src/tokenizer/tokenizer.rs)'s to it.
-
-Tantivy's comes with few tokenizers, but external crates are offering advanced tokenizers, such as [Lindera](https://crates.io/crates/lindera) for Japanese.
-
-
-## [query/](src/query): Define and compose queries
-
-The [Query](src/query/query.rs) trait defines what a query is.
-Due to the necessity for some queries to compute some statistics over the entire index, and because the
-index is composed of several `SegmentReader`, the path from transforming a `Query` to an iterator over documents is slightly convoluted, but fundamentally, this is what a Query is.
-
-The iterator over a document comes with some scoring function. The resulting trait is called a
-[Scorer](src/query/scorer.rs) and is specific to a segment.
-
-Different queries can be combined using the [BooleanQuery](src/query/boolean_query/).
-Tantivy comes with different types of queries and can be extended by implementing
-the `Query`, `Weight`, and `Scorer` traits.
-
-## [collector](src/collector): Define what to do with matched documents
-
-Collectors define how to aggregate the documents matching a query, in the broadest sense possible.
-The search will push matched documents one by one, calling their
-`fn collect(doc: DocId, score: Score);` method.
-
-Users may implement their own collectors by implementing the [Collector](src/collector/mod.rs) trait.
-
-## [query-grammar](query-grammar): Defines the grammar of the query parser
-
-While the [QueryParser](src/query/query_parser/query_parser.rs) struct is located in the `query/` directory, the actual parser combinator used to convert user queries into an AST is in an external crate called `query-grammar`. This part was externalized to lighten the work of the compiler.

AUTHORS

@@ -1,11 +0,0 @@
-# This is the list of authors of tantivy for copyright purposes.
-Paul Masurel
-Laurentiu Nicola
-Dru Sellers
-Ashley Mannix
-Michael J. Curry
-Jason Wolfe
-# As an employee of Google I am required to add Google LLC
-# in the list of authors, but this project is not affiliated to Google
-# in any other way.
-Google LLC 

CHANGELOG.md

@@ -1,332 +1,9 @@
-Tantivy 0.15.3
-=========================
-- Major bugfix. Deleting documents was broken when the index was sorted by a field. (@appaquet, @fulmicoton) #1101
-
-
-Tantivy 0.15.2
-========================
-- Major bugfix. DocStore still panics when a deleted doc is at the beginning of a block. (@appaquet) #1088
-
-Tantivy 0.15.1
-=========================
-- Major bugfix. DocStore panics when first block is deleted. (@appaquet) #1077
-
-Tantivy 0.15.0
-=========================
-- API Changes. Using Range instead of (start, end) in the API and internals (`FileSlice`, `OwnedBytes`, `Snippets`, ...)
-  This change is breaking but migration is trivial.
-- Added an Histogram collector. (@fulmicoton) #994
-- Added support for Option<TCollector>.  (@fulmicoton)
-- DocAddress is now a struct (@scampi) #987
-- Bugfix consistent tie break handling in facet's topk (@hardikpnsp) #357
-- Date field support for range queries (@rihardsk) #516
-- Added lz4-flex as the default compression scheme in tantivy (@PSeitz) #1009
-- Renamed a lot of symbols to avoid all uppercasing on acronyms, as per new clippy recommendation. For instance, RAMDirectory -> RamDirectory. (@fulmicoton)
-- Simplified positions index format (@fulmicoton) #1022
-- Moved bitpacking to bitpacker subcrate and add BlockedBitpacker, which bitpacks blocks of 128 elements (@PSeitz) #1030
-- Added support for more-like-this query in tantivy (@evanxg852000) #1011
-- Added support for sorting an index, e.g presorting documents in an index by a timestamp field. This can heavily improve performance for certain scenarios, by utilizing the sorted data (Top-n optimizations)(@PSeitz). #1026
-- Add iterator over documents in doc store (@PSeitz). #1044
-- Fix log merge policy (@PSeitz). #1043
-- Add detection to avoid small doc store blocks on merge (@PSeitz). #1054
-- Make doc store compression dynamic (@PSeitz). #1060
-- Switch to json for footer version handling (@PSeitz). #1060
-- Updated TermMerger implementation to rely on the union feature of the FST (@scampi) #469
-- Add boolean marking whether position is required in the query_terms API call (@fulmicoton). #1070
-
-
-Tantivy 0.14.0
-=========================
-- Remove dependency to atomicwrites #833 .Implemented by @fulmicoton upon suggestion and research from @asafigan).
-- Migrated tantivy error from the now deprecated `failure` crate to `thiserror` #760. (@hirevo)
-- API Change. Accessing the typed value off a `Schema::Value` now returns an Option instead of panicking if the type does not match.
-- Large API Change in the Directory API. Tantivy used to assume that all files could be somehow memory mapped. After this change, Directory return a `FileSlice` that can be reduced and eventually read into an `OwnedBytes` object. Long and blocking io operation are still required by they do not span over the entire file.
-- Added support for Brotli compression in the DocStore. (@ppodolsky)
-- Added helper for building intersections and unions in BooleanQuery (@guilload)
-- Bugfix in `Query::explain`
-- Removed dependency on `notify` #924. Replaced with `FileWatcher` struct that polls meta file every 500ms in background thread. (@halvorboe @guilload)
-- Added `FilterCollector`, which wraps another collector and filters docs using a predicate over a fast field (@barrotsteindev)
-- Simplified the encoding of the skip reader struct. BlockWAND max tf is now encoded over a single byte. (@fulmicoton)
-- `FilterCollector` now supports all Fast Field value types (@barrotsteindev)
-- FastField are not all loaded when opening the segment reader. (@fulmicoton)
-- Added an API to merge segments, see `tantivy::merge_segments` #1005. (@evanxg852000)
-
-This version breaks compatibility and requires users to reindex everything.
-
-Tantivy 0.13.2
-===================
-Bugfix. Acquiring a facet reader on a segment that does not contain any
-doc with this facet returns `None`. (#896)
-
-Tantivy 0.13.1
-===================
-Made `Query` and `Collector` `Send + Sync`.
-Updated misc dependency versions.
-
-Tantivy 0.13.0
-======================
-Tantivy 0.13 introduce a change in the index format that will require
-you to reindex your index (BlockWAND information are added in the skiplist).
-The index size increase is minor as this information is only added for
-full blocks.
-If you have a massive index for which reindexing is not an option, please contact me
-so that we can discuss possible solutions.
-
-- Bugfix in `FuzzyTermQuery` not matching terms by prefix when it should (@Peachball)
-- Relaxed constraints on the custom/tweak score functions. At the segment level, they can be mut, and they are not required to be Sync + Send.
-- `MMapDirectory::open` does not return a `Result` anymore.
-- Change in the DocSet and Scorer API. (@fulmicoton).
-A freshly created DocSet point directly to their first doc. A sentinel value called TERMINATED marks the end of a DocSet.
-`.advance()` returns the new DocId. `Scorer::skip(target)` has been replaced by `Scorer::seek(target)` and returns the resulting DocId.
-As a result, iterating through DocSet now looks as follows
-```rust
-let mut doc = docset.doc();
-while doc != TERMINATED {
-   // ...
-   doc = docset.advance();
-}
-```
-The change made it possible to greatly simplify a lot of the docset's code.
-- Misc internal optimization and introduction of the `Scorer::for_each_pruning` function. (@fulmicoton)
-- Added an offset option to the Top(.*)Collectors. (@robyoung)
-- Added Block WAND. Performance on TOP-K on term-unions should be greatly increased. (@fulmicoton, and special thanks
-to the PISA team for answering all my questions!)
-
-Tantivy 0.12.0
-======================
-- Removing static dispatch in tokenizers for simplicity. (#762)
-- Added backward iteration for `TermDictionary` stream. (@halvorboe)
-- Fixed a performance issue when searching for the posting lists of a missing term (@audunhalland)
-- Added a configurable maximum number of docs (10M by default) for a segment to be considered for merge (@hntd187, landed by @halvorboe #713)
-- Important Bugfix #777, causing tantivy to retain memory mapping. (diagnosed by @poljar)
-- Added support for field boosting. (#547, @fulmicoton)
-
-## How to update?
-
-Crates relying on custom tokenizer, or registering tokenizer in the manager will require some
-minor changes. Check https://github.com/tantivy-search/tantivy/blob/main/examples/custom_tokenizer.rs
-to check for some code sample.
-
-Tantivy 0.11.3
-=======================
-- Fixed DateTime as a fast field (#735)
-
-Tantivy 0.11.2
-=======================
-- The future returned by `IndexWriter::merge` does not borrow `self` mutably anymore (#732)
-- Exposing a constructor for `WatchHandle` (#731)
-
-Tantivy 0.11.1
-=====================
-- Bug fix #729
-
-
-Tantivy 0.11.0
-=====================
-
-- Added f64 field. Internally reuse u64 code the same way i64 does (@fdb-hiroshima)
-- Various bugfixes in the query parser.
-    - Better handling of hyphens in query parser. (#609)
-    - Better handling of whitespaces.
-- Closes #498 - add support for Elastic-style unbounded range queries for alphanumeric types eg. "title:>hello", "weight:>=70.5", "height:<200" (@petr-tik)
-- API change around `Box<BoxableTokenizer>`. See detail in #629
-- Avoid rebuilding Regex automaton whenever a regex query is reused. #639 (@brainlock)
-- Add footer with some metadata to index files. #605 (@fdb-hiroshima)
-- Add a method to check the compatibility of the footer in the index with the running version of tantivy (@petr-tik)
-- TopDocs collector: ensure stable sorting on equal score. #671 (@brainlock)
-- Added handling of pre-tokenized text fields (#642), which will enable users to
-  load tokens created outside tantivy. See usage in examples/pre_tokenized_text. (@kkoziara)
-- Fix crash when committing multiple times with deleted documents. #681 (@brainlock)
-
-## How to update?
-
-- The index format is changed. You are required to reindex your data to use tantivy 0.11.
-- `Box<dyn BoxableTokenizer>` has been replaced by a `BoxedTokenizer` struct.
-- Regex are now compiled when the `RegexQuery` instance is built. As a result, it can now return
-an error and handling the `Result` is required.
-- `tantivy::version()` now returns a `Version` object. This object implements `ToString()`
-
-Tantivy 0.10.2
-=====================
-
-- Closes #656. Solving memory leak.
-
-Tantivy 0.10.1
-=====================
-
-- Closes #544.  A few users experienced problems with the directory watching system.
-Avoid watching the mmap directory until someone effectively creates a reader that uses
-this functionality.
-
-
-Tantivy 0.10.0
-=====================
-
-*Tantivy 0.10.0 index format is compatible with the index format in 0.9.0.*
-
-- Added an API to easily tweak or entirely replace the
- default score. See `TopDocs::tweak_score`and `TopScore::custom_score` (@fulmicoton)
-- Added an ASCII folding filter (@drusellers)
-- Bugfix in `query.count` in presence of deletes (@fulmicoton)
-- Added `.explain(...)` in `Query` and `Weight` to (@fulmicoton)
-- Added an efficient way to `delete_all_documents` in `IndexWriter` (@petr-tik).
-  All segments are simply removed.
-
-Minor
----------
-- Switched to Rust 2018 (@uvd)
-- Small simplification of the code.
-Calling .freq() or .doc() when .advance() has never been called
-on segment postings should panic from now on.
-- Tokens exceeding `u16::max_value() - 4` chars are discarded silently instead of panicking.
-- Fast fields are now preloaded when the `SegmentReader` is created.
-- `IndexMeta` is now public.  (@hntd187)
-- `IndexWriter` `add_document`, `delete_term`. `IndexWriter` is `Sync`, making it possible to use it with a `
-Arc<RwLock<IndexWriter>>`. `add_document` and `delete_term` can
-only require a read lock. (@fulmicoton)
-- Introducing `Opstamp` as an expressive type alias for `u64`. (@petr-tik)
-- Stamper now relies on `AtomicU64` on all platforms (@petr-tik)
-- Bugfix - Files get deleted slightly earlier
-- Compilation resources improved (@fdb-hiroshima)
-
-## How to update?
-
-Your program should be usable as is.
-
-### Fast fields
-
-Fast fields used to be accessed directly from the `SegmentReader`.
-The API changed, you are now required to acquire your fast field reader via the
-`segment_reader.fast_fields()`, and use one of the typed method:
-- `.u64()`, `.i64()` if your field is single-valued ;
-- `.u64s()`, `.i64s()` if your field is multi-valued ;
-- `.bytes()` if your field is bytes fast field.
-
-
-
-Tantivy 0.9.0
-=====================
-*0.9.0 index format is not compatible with the
-previous index format.*
-- MAJOR BUGFIX :
-  Some `Mmap` objects were being leaked, and would never get released. (@fulmicoton)
-- Removed most unsafe (@fulmicoton)
-- Indexer memory footprint improved. (VInt comp, inlining the first block. (@fulmicoton)
-- Stemming in other language possible (@pentlander)
-- Segments with no docs are deleted earlier (@barrotsteindev)
-- Added grouped add and delete operations.
-  They are guaranteed to happen together (i.e. they cannot be split by a commit).
-  In addition, adds are guaranteed to happen on the same segment. (@elbow-jason)
-- Removed `INT_STORED` and `INT_INDEXED`. It is now possible to use `STORED` and `INDEXED`
-  for int fields. (@fulmicoton)
-- Added DateTime field (@barrotsteindev)
-- Added IndexReader. By default, index is reloaded automatically upon new commits (@fulmicoton)
-- SIMD linear search within blocks (@fulmicoton)
-
-## How to update ?
-
-tantivy 0.9 brought some API breaking change.
-To update from tantivy 0.8, you will need to go through the following steps.
-
-- `schema::INT_INDEXED` and `schema::INT_STORED`  should be replaced by `schema::INDEXED` and `schema::INT_STORED`.
-- The index now does not hold the pool of searcher anymore. You are required to create an intermediary object called
-`IndexReader` for this.
-
-    ```rust
-    // create the reader. You typically need to create 1 reader for the entire
-    // lifetime of you program.
-    let reader = index.reader()?;
-
-    // Acquire a searcher (previously `index.searcher()`) is now written:
-    let searcher = reader.searcher();
-
-    // With the default setting of the reader, you are not required to
-    // call `index.load_searchers()` anymore.
-    //
-    // The IndexReader will pick up that change automatically, regardless
-    // of whether the update was done in a different process or not.
-    // If this behavior is not wanted, you can create your reader with
-    // the `ReloadPolicy::Manual`, and manually decide when to reload the index
-    // by calling `reader.reload()?`.
-
-    ```
-
-
-Tantivy 0.8.2
-=====================
-Fixing build for x86_64 platforms. (#496)
-No need to update from 0.8.1 if tantivy
-is building on your platform.
-
-
-Tantivy 0.8.1
-=====================
-Hotfix of #476.
-
-Merge was reflecting deletes before commit was passed.
-Thanks @barrotsteindev  for reporting the bug.
-
-
-Tantivy 0.8.0
-=====================
-*No change in the index format*
-- API Breaking change in the collector API. (@jwolfe, @fulmicoton)
-- Multithreaded search (@jwolfe, @fulmicoton)
-
-
-Tantivy 0.7.1
-=====================
-*No change in the index format*
-- Bugfix: NGramTokenizer panics on non ascii chars
-- Added a space usage API
-
-Tantivy 0.7
-=====================
-- Skip data for doc ids and positions (@fulmicoton),
-  greatly improving performance
-- Tantivy error now rely on the failure crate (@drusellers)
-- Added support for `AND`, `OR`, `NOT` syntax in addition to the `+`,`-` syntax
-- Added a snippet generator with highlight (@vigneshsarma, @fulmicoton)
-- Added a `TopFieldCollector` (@pentlander)
-
-Tantivy 0.6.1
-=========================
-- Bugfix #324. GC removing was removing file that were still in useful
-- Added support for parsing AllQuery and RangeQuery via QueryParser
-    - AllQuery: `*`
-    - RangeQuery:
-        - Inclusive `field:[startIncl to endIncl]`
-        - Exclusive `field:{startExcl to endExcl}`
-        - Mixed `field:[startIncl to endExcl}` and vice versa
-        - Unbounded `field:[start to *]`, `field:[* to end]`
-
-
-Tantivy 0.6
+Tantivy 0.5.2
 ==========================
 
-Special thanks to @drusellers and @jason-wolfe for their contributions
-to this release!
-
-- Removed C code. Tantivy is now pure Rust. (@fulmicoton)
-- BM25 (@fulmicoton)
-- Approximate field norms encoded over 1 byte. (@fulmicoton)
-- Compiles on stable rust (@fulmicoton)
-- Add &[u8] fastfield for associating arbitrary bytes to each document (@jason-wolfe) (#270)
-    - Completely uncompressed
-    - Internally: One u64 fast field for indexes, one fast field for the bytes themselves.
-- Add NGram token support (@drusellers)
-- Add Stopword Filter support (@drusellers)
-- Add a FuzzyTermQuery (@drusellers)
-- Add a RegexQuery (@drusellers)
-- Various performance improvements (@fulmicoton)_
-
-
-Tantivy 0.5.2
-===========================
-- bugfix #274
-- bugfix #280
-- bugfix #289
-
+- Removed C code. Tantivy is now pure Rust.
+- BM25
+- Approximate field norms encoded over 1 byte.
 
 Tantivy 0.5.1
 ==========================
@@ -404,7 +81,7 @@ Tantivy 0.3
 Special thanks to @Kodraus @lnicola @Ameobea @manuel-woelker @celaus
 for their contribution to this release.
 
-Thanks also to everyone in tantivy gitter chat
+Thanks also to everyone in tantivy gitter chat 
 for their advise and company :)
 
 https://gitter.im/tantivy-search/tantivy
@@ -412,9 +89,9 @@ https://gitter.im/tantivy-search/tantivy
 
 Warning:
 
-Tantivy 0.3 is NOT backward compatible with tantivy 0.2
+Tantivy 0.3 is NOT backward compatible with tantivy 0.2 
 code and index format.
-You should not expect backward compatibility before
+You should not expect backward compatibility before 
 tantivy 1.0.
 
 
@@ -440,7 +117,7 @@ Thanks to @KodrAus ! (#108)
   the natural ordering.
 - Building binary targets for tantivy-cli (Thanks to @KodrAus)
 - Misc invisible bug fixes, and code cleanup.
-- Use
+- Use 
 
 
 

Cargo.toml

@@ -1,114 +1,79 @@
 [package]
 name = "tantivy"
-version = "0.16.0-dev"
+version = "0.5.1"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]
-description = """Search engine library"""
-documentation = "https://docs.rs/tantivy/"
+description = """Tantivy is a search engine library."""
+documentation = "https://tantivy-search.github.io/tantivy/tantivy/index.html"
 homepage = "https://github.com/tantivy-search/tantivy"
 repository = "https://github.com/tantivy-search/tantivy"
 readme = "README.md"
 keywords = ["search", "information", "retrieval"]
-edition = "2018"
 
 [dependencies]
-base64 = "0.13"
-byteorder = "1.4.3"
-crc32fast = "1.2.1"
-once_cell = "1.7.2"
-regex ={ version = "1.5.4", default-features = false, features = ["std"] }
-tantivy-fst = "0.3"
-memmap = {version = "0.7", optional=true}
-lz4_flex = { version = "0.8.0", default-features = false, features = ["checked-decode"], optional = true }
-brotli = { version = "3.3", optional = true }
-snap = { version = "1.0.5", optional = true }
-tempfile = { version = "3.2", optional = true }
-log = "0.4.14"
-serde = { version = "1.0.126", features = ["derive"] }
-serde_json = "1.0.64"
-num_cpus = "1.13"
-fs2={ version = "0.4.3", optional = true }
-levenshtein_automata = "0.2"
-uuid = { version = "0.8.2", features = ["v4", "serde"] }
-crossbeam = "0.8"
-futures = { version = "0.3.15", features = ["thread-pool"] }
-tantivy-query-grammar = { version="0.15.0", path="./query-grammar" }
-tantivy-bitpacker = { version="0.1", path="./bitpacker" }
-common = { version="0.1", path="./common" }
-fastfield_codecs = { version="0.1", path="./fastfield_codecs", default-features = false }
-ownedbytes = { version="0.1", path="./ownedbytes" }
-stable_deref_trait = "1.2"
-rust-stemmers = "1.2"
-downcast-rs = "1.2"
-bitpacking = { version = "0.8.4", default-features = false, features = ["bitpacker4x"] }
-census = "0.4"
-fnv = "1.0.7"
-thiserror = "1.0.24"
-htmlescape = "0.3.1"
-fail = "0.4"
-murmurhash32 = "0.2"
-chrono = "0.4.19"
-smallvec = "1.6.1"
-rayon = "1.5"
-lru = "0.6.5"
-fastdivide = "0.3"
-itertools = "0.10.0"
-measure_time = "0.7.0"
+byteorder = "1.0"
+lazy_static = "0.2.1"
+tinysegmenter = "0.1.0"
+regex = "0.2"
+fst = {version="0.2", default-features=false}
+atomicwrites = {version="0.1", optional=true}
+log = "0.3.6"
+combine = "2.2"
+tempdir = "0.3"
+serde = "1.0"
+serde_derive = "1.0"
+serde_json = "1.0"
+num_cpus = "1.2"
+itertools = "0.5.9"
+bit-set = "0.4.0"
+uuid = { version = "0.6", features = ["v4", "serde"] }
+chan = "0.1"
+crossbeam = "0.3"
+futures = "0.1"
+futures-cpupool = "0.1"
+error-chain = "0.8"
+owning_ref = "0.3"
+stable_deref_trait = "1.0.0"
+rust-stemmers = "0.1.0"
+downcast = { version="0.9", features = ["nightly"]}
+matches = "0.1"
+snap = "0.2"
+bitpacking = {path = "../bitpacking"}
 
 [target.'cfg(windows)'.dependencies]
-winapi = "0.3.9"
+winapi = "0.2"
 
 [dev-dependencies]
-rand = "0.8.3"
-maplit = "1.0.2"
-matches = "0.1.8"
-proptest = "1.0"
-criterion = "0.3.4"
-
-[dev-dependencies.fail]
-version = "0.4"
-features = ["failpoints"]
+rand = "0.3"
+tempfile = "2.1"
+env_logger = "0.4"
 
 [profile.release]
 opt-level = 3
 debug = false
+lto = true
 debug-assertions = false
 
-[profile.test]
-debug-assertions = true
-overflow-checks = true
 
 [features]
-default = ["mmap", "lz4-compression" ]
-mmap = ["fs2", "tempfile", "memmap"]
+default = ["mmap"]
+streamdict = []
+mmap = ["fst/mmap", "atomicwrites"]
 
-brotli-compression = ["brotli"]
-lz4-compression = ["lz4_flex"]
-snappy-compression = ["snap"]
-
-failpoints = ["fail/failpoints"]
-unstable = [] # useful for benches.
-wasm-bindgen = ["uuid/wasm-bindgen"]
-
-[workspace]
-members = ["query-grammar", "bitpacker", "common", "fastfield_codecs", "ownedbytes"]
 
 [badges]
 travis-ci = { repository = "tantivy-search/tantivy" }
 
-# Following the "fail" crate best practises, we isolate
-# tests that define specific behavior in fail check points
-# in a different binary.
-#
-# We do that because, fail rely on a global definition of
-# failpoints behavior and hence, it is incompatible with
-# multithreading.
-[[test]]
-name = "failpoints"
-path = "tests/failpoints/mod.rs"
-required-features = ["fail/failpoints"]
+[[example]]
+name = "simple_search"
+required-features = ["mmap"]
 
-[[bench]]
-name = "analyzer"
-harness = false
+
+[[bin]]
+name = "convert_to_static"
+path = "./bin/convert_to_static.rs"
+
+[[bin]]
+name = "test_static_dir"
+path = "./bin/test_static_dir.rs"

LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2018 by the project authors, as listed in the AUTHORS file. 
+Copyright (c) 2016 Paul Masurel
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
 

Makefile

@@ -1,3 +0,0 @@
-test:
-	echo "Run test only... No examples."
-	cargo test --tests --lib

README.md

@@ -1,134 +1,85 @@
-
-[![Build Status](https://travis-ci.org/tantivy-search/tantivy.svg?branch=main)](https://travis-ci.org/tantivy-search/tantivy)
-[![codecov](https://codecov.io/gh/tantivy-search/tantivy/branch/main/graph/badge.svg)](https://codecov.io/gh/tantivy-search/tantivy)
-[![Join the chat at https://gitter.im/tantivy-search/tantivy](https://badges.gitter.im/tantivy-search/tantivy.svg)](https://gitter.im/tantivy-search/tantivy?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Build status](https://ci.appveyor.com/api/projects/status/r7nb13kj23u8m9pj/branch/main?svg=true)](https://ci.appveyor.com/project/fulmicoton/tantivy/branch/main)
-[![Crates.io](https://img.shields.io/crates/v/tantivy.svg)](https://crates.io/crates/tantivy)
-
 ![Tantivy](https://tantivy-search.github.io/logo/tantivy-logo.png)
 
-[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/0)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/0)
-[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/1)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/1)
-[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/2)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/2)
-[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/3)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/3)
-[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/4)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/4)
-[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/5)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/5)
-[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/6)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/6)
-[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/7)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/7)
+[![Build Status](https://travis-ci.org/tantivy-search/tantivy.svg?branch=master)](https://travis-ci.org/tantivy-search/tantivy)
+[![Coverage Status](https://coveralls.io/repos/github/tantivy-search/tantivy/badge.svg?branch=master&refresh1)](https://coveralls.io/github/tantivy-search/tantivy?branch=master)
+[![Join the chat at https://gitter.im/tantivy-search/tantivy](https://badges.gitter.im/tantivy-search/tantivy.svg)](https://gitter.im/tantivy-search/tantivy?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Build status](https://ci.appveyor.com/api/projects/status/r7nb13kj23u8m9pj?svg=true)](https://ci.appveyor.com/project/fulmicoton/tantivy)
 
-[![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
+**Tantivy** is a **full text search engine library** written in rust.
 
-
-**Tantivy** is a **full text search engine library** written in Rust.
-
-It is closer to [Apache Lucene](https://lucene.apache.org/) than to [Elasticsearch](https://www.elastic.co/products/elasticsearch) or [Apache Solr](https://lucene.apache.org/solr/) in the sense it is not
-an off-the-shelf search engine server, but rather a crate that can be used
-to build such a search engine.
-
-Tantivy is, in fact, strongly inspired by Lucene's design.
-
-# Benchmark
-
-The following [benchmark](https://tantivy-search.github.io/bench/) break downs 
-performance for different type of queries / collection.
-
-Your mileage WILL vary depending on the nature of queries and their load.
+It is strongly inspired by Lucene's design.
 
 # Features
 
-- Full-text search
-- Configurable tokenizer (stemming available for 17 Latin languages with third party support for Chinese ([tantivy-jieba](https://crates.io/crates/tantivy-jieba) and [cang-jie](https://crates.io/crates/cang-jie)), Japanese ([lindera](https://github.com/lindera-morphology/lindera-tantivy) and [tantivy-tokenizer-tiny-segmenter](https://crates.io/crates/tantivy-tokenizer-tiny-segmenter)) and Korean ([lindera](https://github.com/lindera-morphology/lindera-tantivy) + [lindera-ko-dic-builder](https://github.com/lindera-morphology/lindera-ko-dic-builder))
-- Fast (check out the :racehorse: :sparkles: [benchmark](https://tantivy-search.github.io/bench/) :sparkles: :racehorse:)
 - Tiny startup time (<10ms), perfect for command line tools
-- BM25 scoring (the same as Lucene)
-- Natural query language (e.g. `(michael AND jackson) OR "king of pop"`)
-- Phrase queries search (e.g. `"michael jackson"`)
+- tf-idf scoring
+- Basic query language
+- Phrase queries
 - Incremental indexing
 - Multithreaded indexing (indexing English Wikipedia takes < 3 minutes on my desktop)
 - Mmap directory
-- SIMD integer compression when the platform/CPU includes the SSE2 instruction set
-- Single valued and multivalued u64, i64, and f64 fast fields (equivalent of doc values in Lucene)
-- `&[u8]` fast fields
-- Text, i64, u64, f64, dates, and hierarchical facet fields
+- optional SIMD integer compression
+- Single valued and multivalued u64 and i64 fast fields (equivalent of doc values in Lucene)
 - LZ4 compressed document store
 - Range queries
-- Faceted search
-- Configurable indexing (optional term frequency and position indexing)
+- Faceting
+- configurable indexing (optional term frequency and position indexing
 - Cheesy logo with a horse
 
-## Non-features
-
-- Distributed search is out of the scope of Tantivy. That being said, Tantivy is a
-library upon which one could build a distributed search. Serializable/mergeable collector state for instance, 
-are within the scope of Tantivy.
+Tantivy supports Linux, MacOS and Windows.
 
 
 # Getting started
 
-Tantivy works on stable Rust (>= 1.27) and supports Linux, MacOS, and Windows.
+- [tantivy's usage example](http://fulmicoton.com/tantivy-examples/simple_search.html)
+- [tantivy-cli and its tutorial](https://github.com/tantivy-search/tantivy-cli).
+It will walk you through getting a wikipedia search engine up and running in a few minutes.
+- [reference doc]
+    - [For the last released version](https://docs.rs/tantivy/)
+    - [For the last master branch](https://tantivy-search.github.io/tantivy/tantivy/index.html)
 
-- [Tantivy's simple search example](https://tantivy-search.github.io/examples/basic_search.html)
-- [tantivy-cli and its tutorial](https://github.com/tantivy-search/tantivy-cli) - `tantivy-cli` is an actual command line interface that makes it easy for you to create a search engine,
-index documents, and search via the CLI or a small server with a REST API.
-It walks you through getting a wikipedia search engine up and running in a few minutes.
-- [Reference doc for the last released version](https://docs.rs/tantivy/)
+# Compiling
 
-# How can I support this project?
+## Development
 
-There are many ways to support this project. 
+Tantivy requires Rust Nightly because it uses requires the features [`box_syntax`](https://doc.rust-lang.org/stable/unstable-book/language-features/box-syntax.html), [`optin_builtin_traits`](https://github.com/rust-lang/rfcs/blob/master/text/0019-opt-in-builtin-traits.md), [`conservative_impl_trait`](https://github.com/rust-lang/rfcs/blob/master/text/1522-conservative-impl-trait.md),
+and [simd](https://github.com/rust-lang/rust/issues/27731).
 
-- Use Tantivy and tell us about your experience on [Gitter](https://gitter.im/tantivy-search/tantivy) or by email (paul.masurel@gmail.com)
-- Report bugs
-- Write a blog post
-- Help with documentation by asking questions or submitting PRs
-- Contribute code (you can join [our Gitter](https://gitter.im/tantivy-search/tantivy))
-- Talk about Tantivy around you
-- [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
 
-# Contributing code
+To check out and run test, you can simply run :
 
-We use the GitHub Pull Request workflow: reference a GitHub ticket and/or include a comprehensive commit message when opening a PR.
-
-## Clone and build locally
-
-Tantivy compiles on stable Rust but requires `Rust >= 1.27`.
-To check out and run tests, you can simply run:
-
-```bash
-    git clone https://github.com/tantivy-search/tantivy.git
+    git clone git@github.com:tantivy-search/tantivy.git
     cd tantivy
-    cargo build
-```
+    cargo +nightly build
 
-## Run tests
 
-Some tests will not run with just `cargo test` because of `fail-rs`.
-To run the tests exhaustively, run `./run-tests.sh`.
+## Note on release build and performance
 
-## Debug
+If your project depends on `tantivy`, for better performance, make sure to enable
+`sse3` instructions using a RUSTFLAGS. (This instruction set is likely to
+be available on most `x86_64` CPUs you will encounter).
 
-You might find it useful to step through the programme with a debugger.
+For instance,
 
-### A failing test
+    RUSTFLAGS='-C target-feature=+sse3'
 
-Make sure you haven't run `cargo clean` after the most recent `cargo test` or `cargo build` to guarantee that the `target/` directory exists. Use this bash script to find the name of the most recent debug build of Tantivy and run it under `rust-gdb`:
+Or, if you are targetting a specific cpu
 
-```bash
-find target/debug/ -maxdepth 1 -executable -type f -name "tantivy*" -printf '%TY-%Tm-%Td %TT %p\n' | sort -r | cut -d " " -f 3 | xargs -I RECENT_DBG_TANTIVY rust-gdb RECENT_DBG_TANTIVY
-```
+    RUSTFLAGS='-C target-cpu=native' build --release
 
-Now that you are in `rust-gdb`, you can set breakpoints on lines and methods that match your source code and run the debug executable with flags that you normally pass to `cargo test` like this:
+Regardless of the flags you pass, by default `tantivy` will contain `SSE3` instructions.
+If you want to disable those, you can run the following command :
 
-```bash
-$gdb run --test-threads 1 --test $NAME_OF_TEST
-```
+    cargo build --no-default-features
 
-### An example
+Alternatively, if you are trying to compile `tantivy` without simd compression,
+you can disable this functionality. In this case, this submodule is not required
+and you can compile tantivy by using the `--no-default-features` flag.
 
-By default, `rustc` compiles everything in the `examples/` directory in debug mode. This makes it easy for you to make examples to reproduce bugs:
+    cargo build --no-default-features
 
-```bash
-rust-gdb target/debug/examples/$EXAMPLE_NAME
-$ gdb run
-```
+
+# Contribute
+
+Send me an email (paul.masurel at gmail.com) if you want to contribute to tantivy.

appveyor.yml

@@ -4,8 +4,11 @@
 os: Visual Studio 2015
 environment:
   matrix:
-    - channel: stable
+    - channel: nightly
       target: x86_64-pc-windows-msvc
+    - channel: nightly
+      target: x86_64-pc-windows-gnu
+      msys_bits: 64
 
 install:
   - appveyor DownloadFile https://win.rustup.rs/ -FileName rustup-init.exe
@@ -18,6 +21,5 @@ install:
 build: false
 
 test_script:
-  - REM SET RUST_LOG=tantivy,test & cargo test --all --verbose --no-default-features --features lz4-compression --features mmap
-  - REM SET RUST_LOG=tantivy,test & cargo test test_store --verbose --no-default-features --features lz4-compression --features snappy-compression --features brotli-compression --features mmap
-  - REM SET RUST_BACKTRACE=1 & cargo build --examples
+  - REM SET RUST_LOG=tantivy,test & cargo test --verbose
+  - REM SET RUST_BACKTRACE=1 & cargo run --example simple_search

benches/analyzer.rs

@@ -1,22 +0,0 @@
-use criterion::{criterion_group, criterion_main, Criterion};
-use tantivy::tokenizer::TokenizerManager;
-
-const ALICE_TXT: &str = include_str!("alice.txt");
-
-pub fn criterion_benchmark(c: &mut Criterion) {
-    let tokenizer_manager = TokenizerManager::default();
-    let tokenizer = tokenizer_manager.get("default").unwrap();
-    c.bench_function("default-tokenize-alice", |b| {
-        b.iter(|| {
-            let mut word_count = 0;
-            let mut token_stream = tokenizer.token_stream(ALICE_TXT);
-            while token_stream.advance() {
-                word_count += 1;
-            }
-            assert_eq!(word_count, 30_731);
-        })
-    });
-}
-
-criterion_group!(benches, criterion_benchmark);
-criterion_main!(benches);

bin/convert_to_static.rs

@@ -0,0 +1,20 @@
+use std::env;
+use std::path::PathBuf;
+use std::fs::File;
+use std::io::Write;
+extern crate tantivy;
+use tantivy::directory::write_static_from_directory;
+
+fn main() {
+    // Prints each argument on a separate line
+    let  mut args = env::args();
+    args.next().unwrap();
+    let directory_path= args.next().expect("Expect 2 args.<directory_path> <outputfile>");
+    let output_path = args.next().expect("Expect 2 args.<directory_path> <outputfile>");
+    println!("{} => {}", directory_path, output_path);
+    let buffer = write_static_from_directory(&PathBuf::from(directory_path)).unwrap();
+    println!("Read all");
+    let mut output = File::create(output_path).unwrap();
+    output.write_all(&buffer[..]).unwrap();
+    output.flush().unwrap();
+}

bin/test_static_dir.rs

@@ -0,0 +1,51 @@
+use std::env;
+use std::path::PathBuf;
+use std::fs::File;
+use std::io::Write;
+extern crate tantivy;
+use tantivy::directory::{StaticDirectory, write_static_from_directory};
+use tantivy::Index;
+use tantivy::query::QueryParser;
+use tantivy::collector::TopCollector;
+
+
+static DATA: &'static [u8] = include_bytes!("output.bin");
+
+fn run() -> tantivy::Result<()> {
+    // Prints each argument on a separate line
+    let directory = StaticDirectory::open(DATA).unwrap();
+    let index = Index::open_directory(directory).unwrap();
+    index.load_searchers().unwrap();
+    let searcher = index.searcher();
+
+    let schema = index.schema();
+    let title = schema.get_field("title").unwrap();
+    let body = schema.get_field("body").unwrap();
+
+    let query_parser = QueryParser::for_index(&index, vec![title, body]);
+    let query = query_parser.parse_query("sea whale")?;
+
+    let mut top_collector = TopCollector::with_limit(10);
+
+    searcher.search(&*query, &mut top_collector)?;
+
+    let doc_addresses = top_collector.docs();
+
+    // The actual documents still need to be
+    // retrieved from Tantivy's store.
+    //
+    // Since the body field was not configured as stored,
+    // the document returned will only contain
+    // a title.
+
+    for doc_address in doc_addresses {
+        let retrieved_doc = searcher.doc(&doc_address)?;
+        println!("{}", schema.to_json(&retrieved_doc));
+    }
+    Ok(())
+}
+
+
+fn main() {
+    run().unwrap();
+}

bitpacker/Cargo.toml

@@ -1,15 +0,0 @@
-[package]
-name = "tantivy-bitpacker"
-version = "0.1.0"
-edition = "2018"
-authors = ["Paul Masurel <paul.masurel@gmail.com>"]
-license = "MIT"
-categories = []
-description = """Tantivy-sub crate: bitpacking"""
-repository = "https://github.com/tantivy-search/tantivy"
-keywords = []
-
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]

bitpacker/benches/bench.rs

@@ -1,33 +0,0 @@
-#![feature(test)]
-
-extern crate test;
-
-#[cfg(test)]
-mod tests {
-    use tantivy_bitpacker::BlockedBitpacker;
-    use test::Bencher;
-    #[bench]
-    fn bench_blockedbitp_read(b: &mut Bencher) {
-        let mut blocked_bitpacker = BlockedBitpacker::new();
-        for val in 0..=21500 {
-            blocked_bitpacker.add(val * val);
-        }
-        b.iter(|| {
-            let mut out = 0;
-            for val in 0..=21500 {
-                out = blocked_bitpacker.get(val);
-            }
-            out
-        });
-    }
-    #[bench]
-    fn bench_blockedbitp_create(b: &mut Bencher) {
-        b.iter(|| {
-            let mut blocked_bitpacker = BlockedBitpacker::new();
-            for val in 0..=21500 {
-                blocked_bitpacker.add(val * val);
-            }
-            blocked_bitpacker
-        });
-    }
-}

bitpacker/src/bitpacker.rs

@@ -1,142 +0,0 @@
-use std::{convert::TryInto, io};
-
-pub struct BitPacker {
-    mini_buffer: u64,
-    mini_buffer_written: usize,
-}
-impl Default for BitPacker {
-    fn default() -> Self {
-        BitPacker::new()
-    }
-}
-impl BitPacker {
-    pub fn new() -> BitPacker {
-        BitPacker {
-            mini_buffer: 0u64,
-            mini_buffer_written: 0,
-        }
-    }
-
-    #[inline]
-    pub fn write<TWrite: io::Write>(
-        &mut self,
-        val: u64,
-        num_bits: u8,
-        output: &mut TWrite,
-    ) -> io::Result<()> {
-        let val_u64 = val as u64;
-        let num_bits = num_bits as usize;
-        if self.mini_buffer_written + num_bits > 64 {
-            self.mini_buffer |= val_u64.wrapping_shl(self.mini_buffer_written as u32);
-            output.write_all(self.mini_buffer.to_le_bytes().as_ref())?;
-            self.mini_buffer = val_u64.wrapping_shr((64 - self.mini_buffer_written) as u32);
-            self.mini_buffer_written = self.mini_buffer_written + num_bits - 64;
-        } else {
-            self.mini_buffer |= val_u64 << self.mini_buffer_written;
-            self.mini_buffer_written += num_bits;
-            if self.mini_buffer_written == 64 {
-                output.write_all(self.mini_buffer.to_le_bytes().as_ref())?;
-                self.mini_buffer_written = 0;
-                self.mini_buffer = 0u64;
-            }
-        }
-        Ok(())
-    }
-
-    pub fn flush<TWrite: io::Write>(&mut self, output: &mut TWrite) -> io::Result<()> {
-        if self.mini_buffer_written > 0 {
-            let num_bytes = (self.mini_buffer_written + 7) / 8;
-            let bytes = self.mini_buffer.to_le_bytes();
-            output.write_all(&bytes[..num_bytes])?;
-            self.mini_buffer_written = 0;
-            self.mini_buffer = 0;
-        }
-        Ok(())
-    }
-
-    pub fn close<TWrite: io::Write>(&mut self, output: &mut TWrite) -> io::Result<()> {
-        self.flush(output)?;
-        // Padding the write file to simplify reads.
-        output.write_all(&[0u8; 7])?;
-        Ok(())
-    }
-}
-
-#[derive(Clone, Debug, Default)]
-pub struct BitUnpacker {
-    num_bits: u64,
-    mask: u64,
-}
-
-impl BitUnpacker {
-    pub fn new(num_bits: u8) -> BitUnpacker {
-        let mask: u64 = if num_bits == 64 {
-            !0u64
-        } else {
-            (1u64 << num_bits) - 1u64
-        };
-        BitUnpacker {
-            num_bits: u64::from(num_bits),
-            mask,
-        }
-    }
-
-    #[inline]
-    pub fn get(&self, idx: u64, data: &[u8]) -> u64 {
-        if self.num_bits == 0 {
-            return 0u64;
-        }
-        let num_bits = self.num_bits;
-        let mask = self.mask;
-        let addr_in_bits = idx * num_bits;
-        let addr = addr_in_bits >> 3;
-        let bit_shift = addr_in_bits & 7;
-        debug_assert!(
-            addr + 8 <= data.len() as u64,
-            "The fast field field should have been padded with 7 bytes."
-        );
-        let bytes: [u8; 8] = (&data[(addr as usize)..(addr as usize) + 8])
-            .try_into()
-            .unwrap();
-        let val_unshifted_unmasked: u64 = u64::from_le_bytes(bytes);
-        let val_shifted = (val_unshifted_unmasked >> bit_shift) as u64;
-        val_shifted & mask
-    }
-}
-
-#[cfg(test)]
-mod test {
-    use super::{BitPacker, BitUnpacker};
-
-    fn create_fastfield_bitpacker(len: usize, num_bits: u8) -> (BitUnpacker, Vec<u64>, Vec<u8>) {
-        let mut data = Vec::new();
-        let mut bitpacker = BitPacker::new();
-        let max_val: u64 = (1u64 << num_bits as u64) - 1u64;
-        let vals: Vec<u64> = (0u64..len as u64)
-            .map(|i| if max_val == 0 { 0 } else { i % max_val })
-            .collect();
-        for &val in &vals {
-            bitpacker.write(val, num_bits, &mut data).unwrap();
-        }
-        bitpacker.close(&mut data).unwrap();
-        assert_eq!(data.len(), ((num_bits as usize) * len + 7) / 8 + 7);
-        let bitunpacker = BitUnpacker::new(num_bits);
-        (bitunpacker, vals, data)
-    }
-
-    fn test_bitpacker_util(len: usize, num_bits: u8) {
-        let (bitunpacker, vals, data) = create_fastfield_bitpacker(len, num_bits);
-        for (i, val) in vals.iter().enumerate() {
-            assert_eq!(bitunpacker.get(i as u64, &data), *val);
-        }
-    }
-
-    #[test]
-    fn test_bitpacker() {
-        test_bitpacker_util(10, 3);
-        test_bitpacker_util(10, 0);
-        test_bitpacker_util(10, 1);
-        test_bitpacker_util(6, 14);
-        test_bitpacker_util(1000, 14);
-    }
-}

bitpacker/src/blocked_bitpacker.rs

@@ -1,178 +0,0 @@
-use crate::{minmax, BitUnpacker};
-
-use super::{bitpacker::BitPacker, compute_num_bits};
-
-const BLOCK_SIZE: usize = 128;
-
-/// `BlockedBitpacker` compresses data in blocks of
-/// 128 elements, while keeping an index on it
-///
-#[derive(Debug, Clone)]
-pub struct BlockedBitpacker {
-    // bitpacked blocks
-    compressed_blocks: Vec<u8>,
-    // uncompressed data, collected until BLOCK_SIZE
-    buffer: Vec<u64>,
-    offset_and_bits: Vec<BlockedBitpackerEntryMetaData>,
-}
-impl Default for BlockedBitpacker {
-    fn default() -> Self {
-        BlockedBitpacker::new()
-    }
-}
-
-/// `BlockedBitpackerEntryMetaData` encodes the
-/// offset and bit_width into a u64 bit field
-///
-/// This saves some space, since 7byte is more
-/// than enough and also keeps the access fast
-/// because of alignment
-#[derive(Debug, Clone, Default)]
-struct BlockedBitpackerEntryMetaData {
-    encoded: u64,
-    base_value: u64,
-}
-
-impl BlockedBitpackerEntryMetaData {
-    fn new(offset: u64, num_bits: u8, base_value: u64) -> Self {
-        let encoded = offset | (num_bits as u64) << (64 - 8);
-        Self {
-            encoded,
-            base_value,
-        }
-    }
-    fn offset(&self) -> u64 {
-        (self.encoded << 8) >> 8
-    }
-    fn num_bits(&self) -> u8 {
-        (self.encoded >> 56) as u8
-    }
-    fn base_value(&self) -> u64 {
-        self.base_value
-    }
-}
-
-#[test]
-fn metadata_test() {
-    let meta = BlockedBitpackerEntryMetaData::new(50000, 6, 40000);
-    assert_eq!(meta.offset(), 50000);
-    assert_eq!(meta.num_bits(), 6);
-}
-
-impl BlockedBitpacker {
-    pub fn new() -> Self {
-        let mut compressed_blocks = vec![];
-        compressed_blocks.resize(8, 0);
-        Self {
-            compressed_blocks,
-            buffer: vec![],
-            offset_and_bits: vec![],
-        }
-    }
-
-    /// The memory used (inclusive childs)
-    pub fn mem_usage(&self) -> usize {
-        std::mem::size_of::<BlockedBitpacker>()
-            + self.compressed_blocks.capacity()
-            + self.offset_and_bits.capacity()
-                * std::mem::size_of_val(&self.offset_and_bits.get(0).cloned().unwrap_or_default())
-            + self.buffer.capacity()
-                * std::mem::size_of_val(&self.buffer.get(0).cloned().unwrap_or_default())
-    }
-
-    #[inline]
-    pub fn add(&mut self, val: u64) {
-        self.buffer.push(val);
-        if self.buffer.len() == BLOCK_SIZE as usize {
-            self.flush();
-        }
-    }
-
-    pub fn flush(&mut self) {
-        if let Some((min_value, max_value)) = minmax(self.buffer.iter()) {
-            let mut bit_packer = BitPacker::new();
-            let num_bits_block = compute_num_bits(*max_value - min_value);
-            // todo performance: the padding handling could be done better, e.g. use a slice and
-            // return num_bytes written from bitpacker
-            self.compressed_blocks
-                .resize(self.compressed_blocks.len() - 8, 0); // remove padding for bitpacker
-            let offset = self.compressed_blocks.len() as u64;
-            // todo performance: for some bit_width we
-            // can encode multiple vals into the
-            // mini_buffer before checking to flush
-            // (to be done in BitPacker)
-            for val in self.buffer.iter() {
-                bit_packer
-                    .write(
-                        *val - min_value,
-                        num_bits_block,
-                        &mut self.compressed_blocks,
-                    )
-                    .expect("cannot write bitpacking to output"); // write to in memory can't fail
-            }
-            bit_packer.flush(&mut self.compressed_blocks).unwrap();
-            self.offset_and_bits
-                .push(BlockedBitpackerEntryMetaData::new(
-                    offset,
-                    num_bits_block,
-                    *min_value,
-                ));
-
-            self.buffer.clear();
-            self.compressed_blocks
-                .resize(self.compressed_blocks.len() + 8, 0); // add padding for bitpacker
-        }
-    }
-    #[inline]
-    pub fn get(&self, idx: usize) -> u64 {
-        let metadata_pos = idx / BLOCK_SIZE as usize;
-        let pos_in_block = idx % BLOCK_SIZE as usize;
-        if let Some(metadata) = self.offset_and_bits.get(metadata_pos) {
-            let unpacked = BitUnpacker::new(metadata.num_bits()).get(
-                pos_in_block as u64,
-                &self.compressed_blocks[metadata.offset() as usize..],
-            );
-            unpacked + metadata.base_value()
-        } else {
-            self.buffer[pos_in_block]
-        }
-    }
-
-    pub fn iter(&self) -> impl Iterator<Item = u64> + '_ {
-        // todo performance: we could decompress a whole block and cache it instead
-        let bitpacked_elems = self.offset_and_bits.len() * BLOCK_SIZE;
-        let iter = (0..bitpacked_elems)
-            .map(move |idx| self.get(idx))
-            .chain(self.buffer.iter().cloned());
-        iter
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    #[test]
-    fn blocked_bitpacker_empty() {
-        let blocked_bitpacker = BlockedBitpacker::new();
-        assert_eq!(blocked_bitpacker.iter().collect::<Vec<u64>>(), vec![]);
-    }
-    #[test]
-    fn blocked_bitpacker_one() {
-        let mut blocked_bitpacker = BlockedBitpacker::new();
-        blocked_bitpacker.add(50000);
-        assert_eq!(blocked_bitpacker.get(0), 50000);
-        assert_eq!(blocked_bitpacker.iter().collect::<Vec<u64>>(), vec![50000]);
-    }
-    #[test]
-    fn blocked_bitpacker_test() {
-        let mut blocked_bitpacker = BlockedBitpacker::new();
-        for val in 0..21500 {
-            blocked_bitpacker.add(val);
-        }
-        for val in 0..21500 {
-            assert_eq!(blocked_bitpacker.get(val as usize), val);
-        }
-        assert_eq!(blocked_bitpacker.iter().count(), 21500);
-        assert_eq!(blocked_bitpacker.iter().last().unwrap(), 21499);
-    }
-}

bitpacker/src/lib.rs

@@ -1,52 +0,0 @@
-mod bitpacker;
-mod blocked_bitpacker;
-
-pub use crate::bitpacker::BitPacker;
-pub use crate::bitpacker::BitUnpacker;
-pub use crate::blocked_bitpacker::BlockedBitpacker;
-
-/// Computes the number of bits that will be used for bitpacking.
-///
-/// In general the target is the minimum number of bits
-/// required to express the amplitude given in argument.
-///
-/// e.g. If the amplitude is 10, we can store all ints on simply 4bits.
-///
-/// The logic is slightly more convoluted here as for optimization
-/// reasons, we want to ensure that a value spawns over at most 8 bytes
-/// of aligned bytes.
-///
-/// Spanning over 9 bytes is possible for instance, if we do
-/// bitpacking with an amplitude of 63 bits.
-/// In this case, the second int will start on bit
-/// 63 (which belongs to byte 7) and ends at byte 15;
-/// Hence 9 bytes (from byte 7 to byte 15 included).
-///
-/// To avoid this, we force the number of bits to 64bits
-/// when the result is greater than `64-8 = 56 bits`.
-///
-/// Note that this only affects rare use cases spawning over
-/// a very large range of values. Even in this case, it results
-/// in an extra cost of at most 12% compared to the optimal
-/// number of bits.
-pub fn compute_num_bits(n: u64) -> u8 {
-    let amplitude = (64u32 - n.leading_zeros()) as u8;
-    if amplitude <= 64 - 8 {
-        amplitude
-    } else {
-        64
-    }
-}
-
-pub fn minmax<I, T>(mut vals: I) -> Option<(T, T)>
-where
-    I: Iterator<Item = T>,
-    T: Copy + Ord,
-{
-    if let Some(first_el) = vals.next() {
-        return Some(vals.fold((first_el, first_el), |(min_val, max_val), el| {
-            (min_val.min(el), max_val.max(el))
-        }));
-    }
-    None
-}

ci/before_deploy.ps1

@@ -1,23 +0,0 @@
-# This script takes care of packaging the build artifacts that will go in the
-# release zipfile
-
-$SRC_DIR = $PWD.Path
-$STAGE = [System.Guid]::NewGuid().ToString()
-
-Set-Location $ENV:Temp
-New-Item -Type Directory -Name $STAGE
-Set-Location $STAGE
-
-$ZIP = "$SRC_DIR\$($Env:CRATE_NAME)-$($Env:APPVEYOR_REPO_TAG_NAME)-$($Env:TARGET).zip"
-
-# TODO Update this to package the right artifacts
-Copy-Item "$SRC_DIR\target\$($Env:TARGET)\release\hello.exe" '.\'
-
-7z a "$ZIP" *
-
-Push-AppveyorArtifact "$ZIP"
-
-Remove-Item *.* -Force
-Set-Location ..
-Remove-Item $STAGE
-Set-Location $SRC_DIR

ci/before_deploy.sh

@@ -1,33 +0,0 @@
-# This script takes care of building your crate and packaging it for release
-
-set -ex
-
-main() {
-    local src=$(pwd) \
-          stage=
-
-    case $TRAVIS_OS_NAME in
-        linux)
-            stage=$(mktemp -d)
-            ;;
-        osx)
-            stage=$(mktemp -d -t tmp)
-            ;;
-    esac
-
-    test -f Cargo.lock || cargo generate-lockfile
-
-    # TODO Update this to build the artifacts that matter to you
-    cross rustc --bin hello --target $TARGET --release -- -C lto
-
-    # TODO Update this to package the right artifacts
-    cp target/$TARGET/release/hello $stage/
-
-    cd $stage
-    tar czf $src/$CRATE_NAME-$TRAVIS_TAG-$TARGET.tar.gz *
-    cd $src
-
-    rm -rf $stage
-}
-
-main

ci/install.sh

@@ -1,47 +0,0 @@
-set -ex
-
-main() {
-    local target=
-    if [ $TRAVIS_OS_NAME = linux ]; then
-        target=x86_64-unknown-linux-musl
-        sort=sort
-    else
-        target=x86_64-apple-darwin
-        sort=gsort  # for `sort --sort-version`, from brew's coreutils.
-    fi
-
-    # Builds for iOS are done on OSX, but require the specific target to be
-    # installed.
-    case $TARGET in
-        aarch64-apple-ios)
-            rustup target install aarch64-apple-ios
-            ;;
-        armv7-apple-ios)
-            rustup target install armv7-apple-ios
-            ;;
-        armv7s-apple-ios)
-            rustup target install armv7s-apple-ios
-            ;;
-        i386-apple-ios)
-            rustup target install i386-apple-ios
-            ;;
-        x86_64-apple-ios)
-            rustup target install x86_64-apple-ios
-            ;;
-    esac
-
-    # This fetches latest stable release
-    local tag=$(git ls-remote --tags --refs --exit-code https://github.com/japaric/cross \
-                       | cut -d/ -f3 \
-                       | grep -E '^v[0.1.0-9.]+$' \
-                       | $sort --version-sort \
-                       | tail -n1)
-    curl -LSfs https://japaric.github.io/trust/install.sh | \
-        sh -s -- \
-           --force \
-           --git japaric/cross \
-           --tag $tag \
-           --target $target
-}
-
-main

ci/script.sh

@@ -1,30 +0,0 @@
-#!/usr/bin/env bash
-
-# This script takes care of testing your crate
-
-set -ex
-
-main() {
-    if [ ! -z $CODECOV ]; then
-        echo "Codecov"
-        cargo build --verbose && cargo coverage --verbose --all && bash <(curl -s https://codecov.io/bash) -s target/kcov
-    else
-        echo "Build"
-        cross build --target $TARGET
-        if [ ! -z $DISABLE_TESTS ]; then
-            return
-        fi
-        echo "Test"
-        cross test --target $TARGET --no-default-features --features mmap
-        cross test --target $TARGET --no-default-features --features mmap query-grammar
-    fi
-    for example in $(ls examples/*.rs)
-    do
-        cargo run --example  $(basename $example .rs)
-    done
-}
-
-# we don't run the "test phase" when doing deploys
-if [ -z $TRAVIS_TAG ]; then
-    main
-fi

common/Cargo.toml

@@ -1,12 +0,0 @@
-[package]
-name = "common"
-version = "0.1.0"
-authors = ["Paul Masurel <paul@quickwit.io>", "Pascal Seitz <pascal@quickwit.io>"]
-license = "MIT"
-edition = "2018"
-description = "common traits and utility functions used by multiple tantivy subcrates"
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-byteorder = "1.4.3"

common/src/lib.rs

@@ -1,9 +0,0 @@
-pub use byteorder::LittleEndian as Endianness;
-
-mod serialize;
-mod vint;
-mod writer;
-
-pub use serialize::{BinarySerializable, DeserializeFrom, FixedSize};
-pub use vint::{read_u32_vint, read_u32_vint_no_advance, serialize_vint_u32, write_u32_vint, VInt};
-pub use writer::{AntiCallToken, CountingWriter, TerminatingWrite};

common/src/vint.rs

@@ -1,234 +0,0 @@
-use super::BinarySerializable;
-use byteorder::{ByteOrder, LittleEndian};
-use std::io;
-use std::io::Read;
-use std::io::Write;
-
-///   Wrapper over a `u64` that serializes as a variable int.
-#[derive(Clone, Copy, Debug, Eq, PartialEq)]
-pub struct VInt(pub u64);
-
-const STOP_BIT: u8 = 128;
-
-pub fn serialize_vint_u32(val: u32, buf: &mut [u8; 8]) -> &[u8] {
-    const START_2: u64 = 1 << 7;
-    const START_3: u64 = 1 << 14;
-    const START_4: u64 = 1 << 21;
-    const START_5: u64 = 1 << 28;
-
-    const STOP_1: u64 = START_2 - 1;
-    const STOP_2: u64 = START_3 - 1;
-    const STOP_3: u64 = START_4 - 1;
-    const STOP_4: u64 = START_5 - 1;
-
-    const MASK_1: u64 = 127;
-    const MASK_2: u64 = MASK_1 << 7;
-    const MASK_3: u64 = MASK_2 << 7;
-    const MASK_4: u64 = MASK_3 << 7;
-    const MASK_5: u64 = MASK_4 << 7;
-
-    let val = u64::from(val);
-    const STOP_BIT: u64 = 128u64;
-    let (res, num_bytes) = match val {
-        0..=STOP_1 => (val | STOP_BIT, 1),
-        START_2..=STOP_2 => (
-            (val & MASK_1) | ((val & MASK_2) << 1) | (STOP_BIT << (8)),
-            2,
-        ),
-        START_3..=STOP_3 => (
-            (val & MASK_1) | ((val & MASK_2) << 1) | ((val & MASK_3) << 2) | (STOP_BIT << (8 * 2)),
-            3,
-        ),
-        START_4..=STOP_4 => (
-            (val & MASK_1)
-                | ((val & MASK_2) << 1)
-                | ((val & MASK_3) << 2)
-                | ((val & MASK_4) << 3)
-                | (STOP_BIT << (8 * 3)),
-            4,
-        ),
-        _ => (
-            (val & MASK_1)
-                | ((val & MASK_2) << 1)
-                | ((val & MASK_3) << 2)
-                | ((val & MASK_4) << 3)
-                | ((val & MASK_5) << 4)
-                | (STOP_BIT << (8 * 4)),
-            5,
-        ),
-    };
-    LittleEndian::write_u64(&mut buf[..], res);
-    &buf[0..num_bytes]
-}
-
-/// Returns the number of bytes covered by a
-/// serialized vint `u32`.
-///
-/// Expects a buffer data that starts
-/// by the serialized `vint`, scans at most 5 bytes ahead until
-/// it finds the vint final byte.
-///
-/// # May Panic
-/// If the payload does not start by a valid `vint`
-fn vint_len(data: &[u8]) -> usize {
-    for (i, &val) in data.iter().enumerate().take(5) {
-        if val >= STOP_BIT {
-            return i + 1;
-        }
-    }
-    panic!("Corrupted data. Invalid VInt 32");
-}
-
-/// Reads a vint `u32` from a buffer, and
-/// consumes its payload data.
-///
-/// # Panics
-///
-/// If the buffer does not start by a valid
-/// vint payload
-pub fn read_u32_vint(data: &mut &[u8]) -> u32 {
-    let (result, vlen) = read_u32_vint_no_advance(*data);
-    *data = &data[vlen..];
-    result
-}
-
-pub fn read_u32_vint_no_advance(data: &[u8]) -> (u32, usize) {
-    let vlen = vint_len(data);
-    let mut result = 0u32;
-    let mut shift = 0u64;
-    for &b in &data[..vlen] {
-        result |= u32::from(b & 127u8) << shift;
-        shift += 7;
-    }
-    (result, vlen)
-}
-/// Write a `u32` as a vint payload.
-pub fn write_u32_vint<W: io::Write>(val: u32, writer: &mut W) -> io::Result<()> {
-    let mut buf = [0u8; 8];
-    let data = serialize_vint_u32(val, &mut buf);
-    writer.write_all(data)
-}
-
-impl VInt {
-    pub fn val(&self) -> u64 {
-        self.0
-    }
-
-    pub fn deserialize_u64<R: Read>(reader: &mut R) -> io::Result<u64> {
-        VInt::deserialize(reader).map(|vint| vint.0)
-    }
-
-    pub fn serialize_into_vec(&self, output: &mut Vec<u8>) {
-        let mut buffer = [0u8; 10];
-        let num_bytes = self.serialize_into(&mut buffer);
-        output.extend(&buffer[0..num_bytes]);
-    }
-
-    pub fn serialize_into(&self, buffer: &mut [u8; 10]) -> usize {
-        let mut remaining = self.0;
-        for (i, b) in buffer.iter_mut().enumerate() {
-            let next_byte: u8 = (remaining % 128u64) as u8;
-            remaining /= 128u64;
-            if remaining == 0u64 {
-                *b = next_byte | STOP_BIT;
-                return i + 1;
-            } else {
-                *b = next_byte;
-            }
-        }
-        unreachable!();
-    }
-}
-
-impl BinarySerializable for VInt {
-    fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
-        let mut buffer = [0u8; 10];
-        let num_bytes = self.serialize_into(&mut buffer);
-        writer.write_all(&buffer[0..num_bytes])
-    }
-
-    fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
-        let mut bytes = reader.bytes();
-        let mut result = 0u64;
-        let mut shift = 0u64;
-        loop {
-            match bytes.next() {
-                Some(Ok(b)) => {
-                    result |= u64::from(b % 128u8) << shift;
-                    if b >= STOP_BIT {
-                        return Ok(VInt(result));
-                    }
-                    shift += 7;
-                }
-                _ => {
-                    return Err(io::Error::new(
-                        io::ErrorKind::InvalidData,
-                        "Reach end of buffer while reading VInt",
-                    ));
-                }
-            }
-        }
-    }
-}
-
-#[cfg(test)]
-mod tests {
-
-    use super::serialize_vint_u32;
-    use super::BinarySerializable;
-    use super::VInt;
-
-    fn aux_test_vint(val: u64) {
-        let mut v = [14u8; 10];
-        let num_bytes = VInt(val).serialize_into(&mut v);
-        for el in &v[num_bytes..10] {
-            assert_eq!(el, &14u8);
-        }
-        assert!(num_bytes > 0);
-        if num_bytes < 10 {
-            assert!(1u64 << (7 * num_bytes) > val);
-        }
-        if num_bytes > 1 {
-            assert!(1u64 << (7 * (num_bytes - 1)) <= val);
-        }
-        let serdeser_val = VInt::deserialize(&mut &v[..]).unwrap();
-        assert_eq!(val, serdeser_val.0);
-    }
-
-    #[test]
-    fn test_vint() {
-        aux_test_vint(0);
-        aux_test_vint(1);
-        aux_test_vint(5);
-        aux_test_vint(u64::max_value());
-        for i in 1..9 {
-            let power_of_128 = 1u64 << (7 * i);
-            aux_test_vint(power_of_128 - 1u64);
-            aux_test_vint(power_of_128);
-            aux_test_vint(power_of_128 + 1u64);
-        }
-        aux_test_vint(10);
-    }
-
-    fn aux_test_serialize_vint_u32(val: u32) {
-        let mut buffer = [0u8; 10];
-        let mut buffer2 = [0u8; 8];
-        let len_vint = VInt(val as u64).serialize_into(&mut buffer);
-        let res2 = serialize_vint_u32(val, &mut buffer2);
-        assert_eq!(&buffer[..len_vint], res2, "array wrong for {}", val);
-    }
-
-    #[test]
-    fn test_vint_u32() {
-        aux_test_serialize_vint_u32(0);
-        aux_test_serialize_vint_u32(1);
-        aux_test_serialize_vint_u32(5);
-        for i in 1..3 {
-            let power_of_128 = 1u32 << (7 * i);
-            aux_test_serialize_vint_u32(power_of_128 - 1u32);
-            aux_test_serialize_vint_u32(power_of_128);
-            aux_test_serialize_vint_u32(power_of_128 + 1u32);
-        }
-        aux_test_serialize_vint_u32(u32::max_value());
-    }
-}

common/src/writer.rs

@@ -1,114 +0,0 @@
-use std::io::{self, BufWriter, Write};
-
-pub struct CountingWriter<W> {
-    underlying: W,
-    written_bytes: u64,
-}
-
-impl<W: Write> CountingWriter<W> {
-    pub fn wrap(underlying: W) -> CountingWriter<W> {
-        CountingWriter {
-            underlying,
-            written_bytes: 0,
-        }
-    }
-
-    #[inline]
-    pub fn written_bytes(&self) -> u64 {
-        self.written_bytes
-    }
-
-    /// Returns the underlying write object.
-    /// Note that this method does not trigger any flushing.
-    #[inline]
-    pub fn finish(self) -> W {
-        self.underlying
-    }
-}
-
-impl<W: Write> Write for CountingWriter<W> {
-    #[inline]
-    fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
-        let written_size = self.underlying.write(buf)?;
-        self.written_bytes += written_size as u64;
-        Ok(written_size)
-    }
-
-    #[inline]
-    fn write_all(&mut self, buf: &[u8]) -> io::Result<()> {
-        self.underlying.write_all(buf)?;
-        self.written_bytes += buf.len() as u64;
-        Ok(())
-    }
-
-    #[inline]
-    fn flush(&mut self) -> io::Result<()> {
-        self.underlying.flush()
-    }
-}
-
-impl<W: TerminatingWrite> TerminatingWrite for CountingWriter<W> {
-    #[inline]
-    fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
-        self.underlying.terminate_ref(token)
-    }
-}
-
-/// Struct used to prevent from calling [`terminate_ref`](trait.TerminatingWrite#method.terminate_ref) directly
-///
-/// The point is that while the type is public, it cannot be built by anyone
-/// outside of this module.
-pub struct AntiCallToken(());
-
-/// Trait used to indicate when no more write need to be done on a writer
-pub trait TerminatingWrite: Write {
-    /// Indicate that the writer will no longer be used. Internally call terminate_ref.
-    fn terminate(mut self) -> io::Result<()>
-    where
-        Self: Sized,
-    {
-        self.terminate_ref(AntiCallToken(()))
-    }
-
-    /// You should implement this function to define custom behavior.
-    /// This function should flush any buffer it may hold.
-    fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()>;
-}
-
-impl<W: TerminatingWrite + ?Sized> TerminatingWrite for Box<W> {
-    fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
-        self.as_mut().terminate_ref(token)
-    }
-}
-
-impl<W: TerminatingWrite> TerminatingWrite for BufWriter<W> {
-    fn terminate_ref(&mut self, a: AntiCallToken) -> io::Result<()> {
-        self.flush()?;
-        self.get_mut().terminate_ref(a)
-    }
-}
-
-impl<'a> TerminatingWrite for &'a mut Vec<u8> {
-    fn terminate_ref(&mut self, _a: AntiCallToken) -> io::Result<()> {
-        self.flush()
-    }
-}
-
-#[cfg(test)]
-mod test {
-
-    use super::CountingWriter;
-    use std::io::Write;
-
-    #[test]
-    fn test_counting_writer() {
-        let buffer: Vec<u8> = vec![];
-        let mut counting_writer = CountingWriter::wrap(buffer);
-        let bytes = (0u8..10u8).collect::<Vec<u8>>();
-        counting_writer.write_all(&bytes).unwrap();
-        let len = counting_writer.written_bytes();
-        let buffer_restituted: Vec<u8> = counting_writer.finish();
-        assert_eq!(len, 10u64);
-        assert_eq!(buffer_restituted.len(), 10);
-    }
-}

doc/.gitignore

@@ -1 +0,0 @@
-book

doc/book.toml

@@ -1,5 +0,0 @@
-[book]
-authors = ["Paul Masurel"]
-multilingual = false
-src = "src"
-title = "Tantivy, the user guide"

doc/src/SUMMARY.md

@@ -1,15 +0,0 @@
-# Summary
-
-
-
-[Avant Propos](./avant-propos.md)
-
-- [Segments](./basis.md)
-- [Defining your schema](./schema.md)
-- [Facetting](./facetting.md)
-- [Innerworkings](./innerworkings.md)
-  - [Inverted index](./inverted_index.md)
-- [Best practise](./inverted_index.md)
-
-[Frequently Asked Questions](./faq.md)
-[Examples](./examples.md)

doc/src/avant-propos.md

@@ -1,34 +0,0 @@
-# Foreword, what is the scope of tantivy?
-
-> Tantivy is a **search** engine **library** for Rust.
-
-If you are familiar with Lucene, it's an excellent approximation to consider tantivy as Lucene for rust. tantivy is heavily inspired by Lucene's design and
-they both have the same scope and targetted use cases.
-
-If you are not familiar with Lucene, let's break down our little tagline.
-
-- **Search** here means full-text search : fundamentally, tantivy is here to help you
-identify efficiently what are the documents matching a given query in your corpus.
-But modern search UI are so much more : text processing, facetting, autocomplete, fuzzy search, good
-relevancy, collapsing, highlighting, spatial search.
-
-  While some of these features are not available in tantivy yet, all of these are relevant
-  feature requests. Tantivy's objective is to offer a solid toolbox to create the best search
-  experience. But keep in mind this is just a toolbox.
-  Which bring us to the second keyword...
-
-- **Library** means that you will have to write code. tantivy is not an *all-in-one* server solution like elastic search for instance.
-
-  Sometimes a functionality will not be available in tantivy because it is too
-  specific to your use case. By design, tantivy should make it possible to extend
-  the available set of features using the existing rock-solid datastructures.
-
-  Most frequently this will mean writing your own `Collector`, your own `Scorer` or your own
-  `TokenFilter`... Some of your requirements may also be related to
-  something closer to architecture or operations. For instance, you may
-  want to build a large corpus on Hadoop, fine-tune the merge policy to keep your
-  index sharded in a time-wise fashion, or you may want to convert and existing
-  index from a different format.
-
-  Tantivy exposes a lot of low level API to do all of these things.
-  

doc/src/basis.md

@@ -1,77 +0,0 @@
-# Anatomy of an index
-
-## Straight from disk
-
-Tantivy accesses its data using an abstracting trait called `Directory`.
-In theory, one can come and override the data access logic. In practise, the
-trait somewhat assumes that your data can be mapped to memory, and tantivy
-seems deeply married to using `mmap` for its io [^1], and the only persisting
-directory shipped with tantivy is the `MmapDirectory`.
-
-While this design has some downsides, this greatly simplifies the source code of
-tantivy. Caching is also entirely delegated to the OS.
-
-`tantivy` works entirely (or almost) by directly reading the datastructures as they are layed on disk. As a result, the act of opening an indexing does not involve loading different datastructures from the disk into random access memory : starting a process, opening an index, and performing your first query can typically be done in a matter of milliseconds.
-
-This is an interesting property for a command line search engine, or for some multi-tenant log search engine : spawning a new process for each new query can be a perfectly sensible solution in some use case.
-
-In later chapters, we will discuss tantivy's inverted index data layout.
-One key take away is that to achieve great performance, search indexes are extremely compact.
-Of course this is crucial to reduce IO, and ensure that as much of our index can sit in RAM.
-
-Also, whenever possible its data is accessed sequentially. Of course, this is an amazing property when tantivy needs to access the data from your spinning hard disk, but this is also
-critical for performance, if your data is read from and an `SSD` or even already in your pagecache.
-
-
-## Segments, and the log method
-
-That kind of compact layout comes at one cost: it prevents our datastructures from being dynamic.
-In fact, the `Directory` trait does not even allow you to modify part of a file.
-
-To allow the addition / deletion of documents, and create the illusion that
-your index is dynamic (i.e.: adding and deleting documents), tantivy uses a common database trick sometimes referred to as the *log method*.
-
-Let's forget about deletes for a moment.
-
-As you add documents, these documents are processed and stored in a dedicated datastructure, in a `RAM` buffer. This datastructure is not ready for search, but it is useful to receive your data and rearrange it very rapidly.
-
-As you add documents, this buffer will reach its capacity and tantivy will transparently stop adding document to it and start converting this datastructure to its final read-only format on disk. Once written, an brand empty buffer is available to resume adding documents.
-
-The resulting chunk of index obtained after this serialization is called a `Segment`.
-
-> A segment is a self-contained atomic piece of index. It is identified with a UUID, and all of its files are identified using the naming scheme : `<UUID>.*`.
-
-Which brings us to the nature of a tantivy `Index`.
-
-> A tantivy `Index` is a collection of `Segments`.
-
-Physically, this really just means and index is a bunch of segment files in a given `Directory`,
-linked together by a `meta.json` file. This transparency can become extremely handy
-to get tantivy to fit your use case:
-
-*Example 1* You could for instance use hadoop to build a very large search index in a timely manner, copy all of the resulting segment files in the same directory and edit the `meta.json` to get a functional index.[^2]
-
-*Example 2* You could also disable your merge policy and enforce daily segments. Removing data after one week can then be done very efficiently by just editing the `meta.json` and deleting the files associated to segment `D-7`.
-
-
-
-
-
-# Merging
-
-As you index more and more data, your index will accumulate more and more segments.
-Having a lot of small segments is not really optimal. There is a bit of redundancy in having
-all these term dictionary. Also when searching, we will need to do term lookups as many times as we have segments.  It can hurt search performance a bit.
-
-That's where merging or compacting comes into place. Tantivy will continuously consider merge
-opportunities and start merging segments in the background.
-
-
-# Indexing throughput, number of indexing threads
-
-
-
-
-[^1]: This may eventually change.
-
-[^2]: Be careful however. By default these files will not be considered as *managed* by tantivy. This means they will never be garbage collected by tantivy, regardless of whether they become obsolete or not.

doc/src/examples.md

@@ -1,3 +0,0 @@
-# Examples
-
-- [Basic search](/examples/basic_search.html)

doc/src/facetting.md

@@ -1,5 +0,0 @@
-# Facetting
-
-wewew
-
-## weeewe

doc/src/innerworkings.md

@@ -1 +0,0 @@
-# Innerworkings

doc/src/inverted_index.md

@@ -1 +0,0 @@
-# Inverted index

doc/src/schema.md

@@ -1 +0,0 @@
-# Defining your schema

examples/custom_collector.rs

@@ -1,182 +0,0 @@
-// # Custom collector example
-//
-// This example shows how you can implement your own
-// collector. As an example, we will compute a collector
-// that computes the standard deviation of a given fast field.
-//
-// Of course, you can have a look at the tantivy's built-in collectors
-// such as the `CountCollector` for more examples.
-
-// ---
-// Importing tantivy...
-use tantivy::collector::{Collector, SegmentCollector};
-use tantivy::fastfield::{DynamicFastFieldReader, FastFieldReader};
-use tantivy::query::QueryParser;
-use tantivy::schema::Field;
-use tantivy::schema::{Schema, FAST, INDEXED, TEXT};
-use tantivy::{doc, Index, Score, SegmentReader};
-
-#[derive(Default)]
-struct Stats {
-    count: usize,
-    sum: f64,
-    squared_sum: f64,
-}
-
-impl Stats {
-    pub fn count(&self) -> usize {
-        self.count
-    }
-
-    pub fn mean(&self) -> f64 {
-        self.sum / (self.count as f64)
-    }
-
-    fn square_mean(&self) -> f64 {
-        self.squared_sum / (self.count as f64)
-    }
-
-    pub fn standard_deviation(&self) -> f64 {
-        let mean = self.mean();
-        (self.square_mean() - mean * mean).sqrt()
-    }
-
-    fn non_zero_count(self) -> Option<Stats> {
-        if self.count == 0 {
-            None
-        } else {
-            Some(self)
-        }
-    }
-}
-
-struct StatsCollector {
-    field: Field,
-}
-
-impl StatsCollector {
-    fn with_field(field: Field) -> StatsCollector {
-        StatsCollector { field }
-    }
-}
-
-impl Collector for StatsCollector {
-    // That's the type of our result.
-    // Our standard deviation will be a float.
-    type Fruit = Option<Stats>;
-
-    type Child = StatsSegmentCollector;
-
-    fn for_segment(
-        &self,
-        _segment_local_id: u32,
-        segment_reader: &SegmentReader,
-    ) -> tantivy::Result<StatsSegmentCollector> {
-        let fast_field_reader = segment_reader.fast_fields().u64(self.field)?;
-        Ok(StatsSegmentCollector {
-            fast_field_reader,
-            stats: Stats::default(),
-        })
-    }
-
-    fn requires_scoring(&self) -> bool {
-        // this collector does not care about score.
-        false
-    }
-
-    fn merge_fruits(&self, segment_stats: Vec<Option<Stats>>) -> tantivy::Result<Option<Stats>> {
-        let mut stats = Stats::default();
-        for segment_stats_opt in segment_stats {
-            if let Some(segment_stats) = segment_stats_opt {
-                stats.count += segment_stats.count;
-                stats.sum += segment_stats.sum;
-                stats.squared_sum += segment_stats.squared_sum;
-            }
-        }
-        Ok(stats.non_zero_count())
-    }
-}
-
-struct StatsSegmentCollector {
-    fast_field_reader: DynamicFastFieldReader<u64>,
-    stats: Stats,
-}
-
-impl SegmentCollector for StatsSegmentCollector {
-    type Fruit = Option<Stats>;
-
-    fn collect(&mut self, doc: u32, _score: Score) {
-        let value = self.fast_field_reader.get(doc) as f64;
-        self.stats.count += 1;
-        self.stats.sum += value;
-        self.stats.squared_sum += value * value;
-    }
-
-    fn harvest(self) -> <Self as SegmentCollector>::Fruit {
-        self.stats.non_zero_count()
-    }
-}
-
-fn main() -> tantivy::Result<()> {
-    // # Defining the schema
-    //
-    // The Tantivy index requires a very strict schema.
-    // The schema declares which fields are in the index,
-    // and for each field, its type and "the way it should
-    // be indexed".
-
-    // first we need to define a schema ...
-    let mut schema_builder = Schema::builder();
-
-    // We'll assume a fictional index containing
-    // products, and with a name, a description, and a price.
-    let product_name = schema_builder.add_text_field("name", TEXT);
-    let product_description = schema_builder.add_text_field("description", TEXT);
-    let price = schema_builder.add_u64_field("price", INDEXED | FAST);
-    let schema = schema_builder.build();
-
-    // # Indexing documents
-    //
-    // Lets index a bunch of fake documents for the sake of
-    // this example.
-    let index = Index::create_in_ram(schema);
-
-    let mut index_writer = index.writer(50_000_000)?;
-    index_writer.add_document(doc!(
-        product_name => "Super Broom 2000",
-        product_description => "While it is ok for short distance travel, this broom \
-        was designed quiditch. It will up your game.",
-        price => 30_200u64
-    ));
-    index_writer.add_document(doc!(
-        product_name => "Turbulobroom",
-        product_description => "You might have heard of this broom before : it is the sponsor of the Wales team.\
-            You'll enjoy its sharp turns, and rapid acceleration",
-        price => 29_240u64
-    ));
-    index_writer.add_document(doc!(
-        product_name => "Broomio",
-        product_description => "Great value for the price. This broom is a market favorite",
-        price => 21_240u64
-    ));
-    index_writer.add_document(doc!(
-        product_name => "Whack a Mole",
-        product_description => "Prime quality bat.",
-        price => 5_200u64
-    ));
-    index_writer.commit()?;
-
-    let reader = index.reader()?;
-    let searcher = reader.searcher();
-    let query_parser = QueryParser::for_index(&index, vec![product_name, product_description]);
-
-    // here we want to get a hit on the 'ken' in Frankenstein
-    let query = query_parser.parse_query("broom")?;
-    if let Some(stats) = searcher.search(&query, &StatsCollector::with_field(price))? {
-        println!("count: {}", stats.count());
-        println!("mean: {}", stats.mean());
-        println!("standard deviation: {}", stats.standard_deviation());
-    }
-
-    Ok(())
-}

examples/custom_tokenizer.rs

@@ -1,112 +0,0 @@
-// # Defining a tokenizer pipeline
-//
-// In this example, we'll see how to define a tokenizer pipeline
-// by aligning a bunch of `TokenFilter`.
-use tantivy::collector::TopDocs;
-use tantivy::query::QueryParser;
-use tantivy::schema::*;
-use tantivy::tokenizer::NgramTokenizer;
-use tantivy::{doc, Index};
-
-fn main() -> tantivy::Result<()> {
-    // # Defining the schema
-    //
-    // The Tantivy index requires a very strict schema.
-    // The schema declares which fields are in the index,
-    // and for each field, its type and "the way it should
-    // be indexed".
-
-    // first we need to define a schema ...
-    let mut schema_builder = Schema::builder();
-
-    // Our first field is title.
-    // In this example we want to use NGram searching
-    // we will set that to 3 characters, so any three
-    // char in the title should be findable.
-    let text_field_indexing = TextFieldIndexing::default()
-        .set_tokenizer("ngram3")
-        .set_index_option(IndexRecordOption::WithFreqsAndPositions);
-    let text_options = TextOptions::default()
-        .set_indexing_options(text_field_indexing)
-        .set_stored();
-    let title = schema_builder.add_text_field("title", text_options);
-
-    // Our second field is body.
-    // We want full-text search for it, but we do not
-    // need to be able to be able to retrieve it
-    // for our application.
-    //
-    // We can make our index lighter and
-    // by omitting `STORED` flag.
-    let body = schema_builder.add_text_field("body", TEXT);
-
-    let schema = schema_builder.build();
-
-    // # Indexing documents
-    //
-    // Let's create a brand new index.
-    // To simplify we will work entirely in RAM.
-    // This is not what you want in reality, but it is very useful
-    // for your unit tests... Or this example.
-    let index = Index::create_in_ram(schema.clone());
-
-    // here we are registering our custome tokenizer
-    // this will store tokens of 3 characters each
-    index
-        .tokenizers()
-        .register("ngram3", NgramTokenizer::new(3, 3, false));
-
-    // To insert document we need an index writer.
-    // There must be only one writer at a time.
-    // This single `IndexWriter` is already
-    // multithreaded.
-    //
-    // Here we use a buffer of 50MB per thread. Using a bigger
-    // heap for the indexer can increase its throughput.
-    let mut index_writer = index.writer(50_000_000)?;
-    index_writer.add_document(doc!(
-    title => "The Old Man and the Sea",
-    body => "He was an old man who fished alone in a skiff in the Gulf Stream and \
-     he had gone eighty-four days now without taking a fish."
-    ));
-    index_writer.add_document(doc!(
-    title => "Of Mice and Men",
-       body => r#"A few miles south of Soledad, the Salinas River drops in close to the hillside
-                bank and runs deep and green. The water is warm too, for it has slipped twinkling
-                over the yellow sands in the sunlight before reaching the narrow pool. On one
-                side of the river the golden foothill slopes curve up to the strong and rocky
-                Gabilan Mountains, but on the valley side the water is lined with trees—willows
-                fresh and green with every spring, carrying in their lower leaf junctures the
-                debris of the winter’s flooding; and sycamores with mottled, white, recumbent
-                limbs and branches that arch over the pool"#
-    ));
-    index_writer.add_document(doc!(
-    title => "Frankenstein",
-        body => r#"You will rejoice to hear that no disaster has accompanied the commencement of an
-                enterprise which you have regarded with such evil forebodings.  I arrived here
-                yesterday, and my first task is to assure my dear sister of my welfare and
-                increasing confidence in the success of my undertaking."#
-    ));
-    index_writer.commit()?;
-
-    let reader = index.reader()?;
-    let searcher = reader.searcher();
-
-    // The query parser can interpret human queries.
-    // Here, if the user does not specify which
-    // field they want to search, tantivy will search
-    // in both title and body.
-    let query_parser = QueryParser::for_index(&index, vec![title, body]);
-
-    // here we want to get a hit on the 'ken' in Frankenstein
-    let query = query_parser.parse_query("ken")?;
-
-    let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
-
-    for (_, doc_address) in top_docs {
-        let retrieved_doc = searcher.doc(doc_address)?;
-        println!("{}", schema.to_json(&retrieved_doc));
-    }
-
-    Ok(())
-}

examples/deleting_updating_documents.rs

@@ -1,143 +0,0 @@
-// # Deleting and Updating (?) documents
-//
-// This example explains how to delete and update documents.
-// In fact there is actually no such thing as an update in tantivy.
-//
-// To update a document, you need to delete a document and then reinsert
-// its new version.
-//
-// ---
-// Importing tantivy...
-use tantivy::collector::TopDocs;
-use tantivy::query::TermQuery;
-use tantivy::schema::*;
-use tantivy::{doc, Index, IndexReader};
-
-// A simple helper function to fetch a single document
-// given its id from our index.
-// It will be helpful to check our work.
-fn extract_doc_given_isbn(
-    reader: &IndexReader,
-    isbn_term: &Term,
-) -> tantivy::Result<Option<Document>> {
-    let searcher = reader.searcher();
-
-    // This is the simplest query you can think of.
-    // It matches all of the documents containing a specific term.
-    //
-    // The second argument is here to tell we don't care about decoding positions,
-    // or term frequencies.
-    let term_query = TermQuery::new(isbn_term.clone(), IndexRecordOption::Basic);
-    let top_docs = searcher.search(&term_query, &TopDocs::with_limit(1))?;
-
-    if let Some((_score, doc_address)) = top_docs.first() {
-        let doc = searcher.doc(*doc_address)?;
-        Ok(Some(doc))
-    } else {
-        // no doc matching this ID.
-        Ok(None)
-    }
-}
-
-fn main() -> tantivy::Result<()> {
-    // # Defining the schema
-    //
-    // Check out the *basic_search* example if this makes
-    // small sense to you.
-    let mut schema_builder = Schema::builder();
-
-    // Tantivy does not really have a notion of primary id.
-    // This may change in the future.
-    //
-    // Still, we can create a `isbn` field and use it as an id. This
-    // field can be `u64` or a `text`, depending on your use case.
-    // It just needs to be indexed.
-    //
-    // If it is `text`, let's make sure to keep it `raw` and let's avoid
-    // running any text processing on it.
-    // This is done by associating this field to the tokenizer named `raw`.
-    // Rather than building our [`TextOptions`](//docs.rs/tantivy/~0/tantivy/schema/struct.TextOptions.html) manually,
-    // We use the `STRING` shortcut. `STRING` stands for indexed (without term frequency or positions)
-    // and untokenized.
-    //
-    // Because we also want to be able to see this `id` in our returned documents,
-    // we also mark the field as stored.
-    let isbn = schema_builder.add_text_field("isbn", STRING | STORED);
-    let title = schema_builder.add_text_field("title", TEXT | STORED);
-    let schema = schema_builder.build();
-
-    let index = Index::create_in_ram(schema.clone());
-
-    let mut index_writer = index.writer(50_000_000)?;
-
-    // Let's add a couple of documents, for the sake of the example.
-    let mut old_man_doc = Document::default();
-    old_man_doc.add_text(title, "The Old Man and the Sea");
-    index_writer.add_document(doc!(
-        isbn => "978-0099908401",
-        title => "The old Man and the see"
-    ));
-    index_writer.add_document(doc!(
-        isbn => "978-0140177398",
-        title => "Of Mice and Men",
-    ));
-    index_writer.add_document(doc!(
-       title => "Frankentein", //< Oops there is a typo here.
-       isbn => "978-9176370711",
-    ));
-    index_writer.commit()?;
-    let reader = index.reader()?;
-
-    let frankenstein_isbn = Term::from_field_text(isbn, "978-9176370711");
-
-    // Oops our frankenstein doc seems misspelled
-    let frankenstein_doc_misspelled = extract_doc_given_isbn(&reader, &frankenstein_isbn)?.unwrap();
-    assert_eq!(
-        schema.to_json(&frankenstein_doc_misspelled),
-        r#"{"isbn":["978-9176370711"],"title":["Frankentein"]}"#,
-    );
-
-    // # Update = Delete + Insert
-    //
-    // Here we will want to update the typo in the `Frankenstein` book.
-    //
-    // Tantivy does not handle updates directly, we need to delete
-    // and reinsert the document.
-    //
-    // This can be complicated as it means you need to have access
-    // to the entire document. It is good practise to integrate tantivy
-    // with a key value store for this reason.
-    //
-    // To remove one of the document, we just call `delete_term`
-    // on its id.
-    //
-    // Note that `tantivy` does nothing to enforce the idea that
-    // there is only one document associated to this id.
-    //
-    // Also you might have noticed that we apply the delete before
-    // having committed. This does not matter really...
-    index_writer.delete_term(frankenstein_isbn.clone());
-
-    // We now need to reinsert our document without the typo.
-    index_writer.add_document(doc!(
-       title => "Frankenstein",
-       isbn => "978-9176370711",
-    ));
-
-    // You are guaranteed that your clients will only observe your index in
-    // the state it was in after a commit.
-    // In this example, your search engine will at no point be missing the *Frankenstein* document.
-    // Everything happened as if the document was updated.
-    index_writer.commit()?;
-    // We reload our searcher to make our change available to clients.
-    reader.reload()?;
-
-    // No more typo!
-    let frankenstein_new_doc = extract_doc_given_isbn(&reader, &frankenstein_isbn)?.unwrap();
-    assert_eq!(
-        schema.to_json(&frankenstein_new_doc),
-        r#"{"isbn":["978-9176370711"],"title":["Frankenstein"]}"#,
-    );
-
-    Ok(())
-}

examples/faceted_search.rs

@@ -1,112 +0,0 @@
-// # Basic Example
-//
-// This example covers the basic functionalities of
-// tantivy.
-//
-// We will :
-// - define our schema
-// = create an index in a directory
-// - index few documents in our index
-// - search for the best document matchings "sea whale"
-// - retrieve the best document original content.
-
-// ---
-// Importing tantivy...
-use tantivy::collector::FacetCollector;
-use tantivy::query::{AllQuery, TermQuery};
-use tantivy::schema::*;
-use tantivy::{doc, Index};
-
-fn main() -> tantivy::Result<()> {
-    // Let's create a temporary directory for the sake of this example
-    let mut schema_builder = Schema::builder();
-
-    let name = schema_builder.add_text_field("felin_name", TEXT | STORED);
-    // this is our faceted field: its scientific classification
-    let classification = schema_builder.add_facet_field("classification", INDEXED);
-
-    let schema = schema_builder.build();
-    let index = Index::create_in_ram(schema);
-
-    let mut index_writer = index.writer(30_000_000)?;
-
-    // For convenience, tantivy also comes with a macro to
-    // reduce the boilerplate above.
-    index_writer.add_document(doc!(
-        name => "Cat",
-        classification => Facet::from("/Felidae/Felinae/Felis")
-    ));
-    index_writer.add_document(doc!(
-        name => "Canada lynx",
-        classification => Facet::from("/Felidae/Felinae/Lynx")
-    ));
-    index_writer.add_document(doc!(
-        name => "Cheetah",
-        classification => Facet::from("/Felidae/Felinae/Acinonyx")
-    ));
-    index_writer.add_document(doc!(
-        name => "Tiger",
-        classification => Facet::from("/Felidae/Pantherinae/Panthera")
-    ));
-    index_writer.add_document(doc!(
-        name => "Lion",
-        classification => Facet::from("/Felidae/Pantherinae/Panthera")
-    ));
-    index_writer.add_document(doc!(
-        name => "Jaguar",
-        classification => Facet::from("/Felidae/Pantherinae/Panthera")
-    ));
-    index_writer.add_document(doc!(
-        name => "Sunda clouded leopard",
-        classification => Facet::from("/Felidae/Pantherinae/Neofelis")
-    ));
-    index_writer.add_document(doc!(
-        name => "Fossa",
-        classification => Facet::from("/Eupleridae/Cryptoprocta")
-    ));
-    index_writer.commit()?;
-
-    let reader = index.reader()?;
-    let searcher = reader.searcher();
-    {
-        let mut facet_collector = FacetCollector::for_field(classification);
-        facet_collector.add_facet("/Felidae");
-        let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
-        // This lists all of the facet counts, right below "/Felidae".
-        let facets: Vec<(&Facet, u64)> = facet_counts.get("/Felidae").collect();
-        assert_eq!(
-            facets,
-            vec![
-                (&Facet::from("/Felidae/Felinae"), 3),
-                (&Facet::from("/Felidae/Pantherinae"), 4),
-            ]
-        );
-    }
-
-    // Facets are also searchable.
-    //
-    // For instance a common UI pattern is to allow the user someone to click on a facet link
-    // (e.g: `Pantherinae`) to drill down and filter the current result set with this subfacet.
-    //
-    // The search would then look as follows.
-
-    // Check the reference doc for different ways to create a `Facet` object.
-    {
-        let facet = Facet::from("/Felidae/Pantherinae");
-        let facet_term = Term::from_facet(classification, &facet);
-        let facet_term_query = TermQuery::new(facet_term, IndexRecordOption::Basic);
-        let mut facet_collector = FacetCollector::for_field(classification);
-        facet_collector.add_facet("/Felidae/Pantherinae");
-        let facet_counts = searcher.search(&facet_term_query, &facet_collector)?;
-        let facets: Vec<(&Facet, u64)> = facet_counts.get("/Felidae/Pantherinae").collect();
-        assert_eq!(
-            facets,
-            vec![
-                (&Facet::from("/Felidae/Pantherinae/Neofelis"), 1),
-                (&Facet::from("/Felidae/Pantherinae/Panthera"), 3),
-            ]
-        );
-    }
-
-    Ok(())
-}

examples/faceted_search_with_tweaked_score.rs

@@ -1,98 +0,0 @@
-use std::collections::HashSet;
-use tantivy::collector::TopDocs;
-use tantivy::doc;
-use tantivy::query::BooleanQuery;
-use tantivy::schema::*;
-use tantivy::{DocId, Index, Score, SegmentReader};
-
-fn main() -> tantivy::Result<()> {
-    let mut schema_builder = Schema::builder();
-
-    let title = schema_builder.add_text_field("title", STORED);
-    let ingredient = schema_builder.add_facet_field("ingredient", INDEXED);
-
-    let schema = schema_builder.build();
-    let index = Index::create_in_ram(schema);
-
-    let mut index_writer = index.writer(30_000_000)?;
-
-    index_writer.add_document(doc!(
-        title => "Fried egg",
-        ingredient => Facet::from("/ingredient/egg"),
-        ingredient => Facet::from("/ingredient/oil"),
-    ));
-    index_writer.add_document(doc!(
-        title => "Scrambled egg",
-        ingredient => Facet::from("/ingredient/egg"),
-        ingredient => Facet::from("/ingredient/butter"),
-        ingredient => Facet::from("/ingredient/milk"),
-        ingredient => Facet::from("/ingredient/salt"),
-    ));
-    index_writer.add_document(doc!(
-        title => "Egg rolls",
-        ingredient => Facet::from("/ingredient/egg"),
-        ingredient => Facet::from("/ingredient/garlic"),
-        ingredient => Facet::from("/ingredient/salt"),
-        ingredient => Facet::from("/ingredient/oil"),
-        ingredient => Facet::from("/ingredient/tortilla-wrap"),
-        ingredient => Facet::from("/ingredient/mushroom"),
-    ));
-    index_writer.commit()?;
-
-    let reader = index.reader()?;
-    let searcher = reader.searcher();
-    {
-        let facets = vec![
-            Facet::from("/ingredient/egg"),
-            Facet::from("/ingredient/oil"),
-            Facet::from("/ingredient/garlic"),
-            Facet::from("/ingredient/mushroom"),
-        ];
-        let query = BooleanQuery::new_multiterms_query(
-            facets
-                .iter()
-                .map(|key| Term::from_facet(ingredient, key))
-                .collect(),
-        );
-        let top_docs_by_custom_score =
-            TopDocs::with_limit(2).tweak_score(move |segment_reader: &SegmentReader| {
-                let ingredient_reader = segment_reader.facet_reader(ingredient).unwrap();
-                let facet_dict = ingredient_reader.facet_dict();
-
-                let query_ords: HashSet<u64> = facets
-                    .iter()
-                    .filter_map(|key| facet_dict.term_ord(key.encoded_str()).unwrap())
-                    .collect();
-
-                let mut facet_ords_buffer: Vec<u64> = Vec::with_capacity(20);
-
-                move |doc: DocId, original_score: Score| {
-                    ingredient_reader.facet_ords(doc, &mut facet_ords_buffer);
-                    let missing_ingredients = facet_ords_buffer
-                        .iter()
-                        .filter(|ord| !query_ords.contains(ord))
-                        .count();
-                    let tweak = 1.0 / 4_f32.powi(missing_ingredients as i32);
-
-                    original_score * tweak
-                }
-            });
-        let top_docs = searcher.search(&query, &top_docs_by_custom_score)?;
-
-        let titles: Vec<String> = top_docs
-            .iter()
-            .map(|(_, doc_id)| {
-                searcher
-                    .doc(*doc_id)
-                    .unwrap()
-                    .get_first(title)
-                    .unwrap()
-                    .text()
-                    .unwrap()
-                    .to_owned()
-            })
-            .collect();
-        assert_eq!(titles, vec!["Fried egg", "Egg rolls"]);
-    }
-    Ok(())
-}

examples/generate_html.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+docco simple_search.rs -o html

examples/html/docco.css

@@ -0,0 +1,518 @@
+/*--------------------- Typography ----------------------------*/
+
+@font-face {
+    font-family: 'aller-light';
+    src: url('public/fonts/aller-light.eot');
+    src: url('public/fonts/aller-light.eot?#iefix') format('embedded-opentype'),
+         url('public/fonts/aller-light.woff') format('woff'),
+         url('public/fonts/aller-light.ttf') format('truetype');
+    font-weight: normal;
+    font-style: normal;
+}
+
+@font-face {
+    font-family: 'aller-bold';
+    src: url('public/fonts/aller-bold.eot');
+    src: url('public/fonts/aller-bold.eot?#iefix') format('embedded-opentype'),
+         url('public/fonts/aller-bold.woff') format('woff'),
+         url('public/fonts/aller-bold.ttf') format('truetype');
+    font-weight: normal;
+    font-style: normal;
+}
+
+@font-face {
+    font-family: 'roboto-black';
+    src: url('public/fonts/roboto-black.eot');
+    src: url('public/fonts/roboto-black.eot?#iefix') format('embedded-opentype'),
+         url('public/fonts/roboto-black.woff') format('woff'),
+         url('public/fonts/roboto-black.ttf') format('truetype');
+    font-weight: normal;
+    font-style: normal;
+}
+
+/*--------------------- Layout ----------------------------*/
+html { height: 100%; }
+body {
+  font-family: "aller-light";
+  font-size: 14px;
+  line-height: 18px;
+  color: #30404f;
+  margin: 0; padding: 0;
+  height:100%;
+}
+#container { min-height: 100%; }
+
+a {
+  color: #000;
+}
+
+b, strong {
+  font-weight: normal;
+  font-family: "aller-bold";
+}
+
+p {
+  margin: 15px 0 0px;
+}
+  .annotation ul, .annotation ol {
+    margin: 25px 0;
+  }
+    .annotation ul li, .annotation ol li {
+      font-size: 14px;
+      line-height: 18px;
+      margin: 10px 0;
+    }
+
+h1, h2, h3, h4, h5, h6 {
+  color: #112233;
+  line-height: 1em;
+  font-weight: normal;
+  font-family: "roboto-black";
+  text-transform: uppercase;
+  margin: 30px 0 15px 0;
+}
+
+h1 {
+  margin-top: 40px;
+}
+h2 {
+  font-size: 1.26em;
+}
+
+hr {
+  border: 0;
+  background: 1px #ddd;
+  height: 1px;
+  margin: 20px 0;
+}
+
+pre, tt, code {
+  font-size: 12px; line-height: 16px;
+  font-family: Menlo, Monaco, Consolas, "Lucida Console", monospace;
+  margin: 0; padding: 0;
+}
+  .annotation pre {
+    display: block;
+    margin: 0;
+    padding: 7px 10px;
+    background: #fcfcfc;
+    -moz-box-shadow:    inset 0 0 10px rgba(0,0,0,0.1);
+    -webkit-box-shadow: inset 0 0 10px rgba(0,0,0,0.1);
+    box-shadow:         inset 0 0 10px rgba(0,0,0,0.1);
+    overflow-x: auto;
+  }
+    .annotation pre code {
+      border: 0;
+      padding: 0;
+      background: transparent;
+    }
+
+
+blockquote {
+  border-left: 5px solid #ccc;
+  margin: 0;
+  padding: 1px 0 1px 1em;
+}
+  .sections blockquote p {
+    font-family: Menlo, Consolas, Monaco, monospace;
+    font-size: 12px; line-height: 16px;
+    color: #999;
+    margin: 10px 0 0;
+    white-space: pre-wrap;
+  }
+
+ul.sections {
+  list-style: none;
+  padding:0 0 5px 0;;
+  margin:0;
+}
+
+/*
+  Force border-box so that % widths fit the parent
+  container without overlap because of margin/padding.
+
+  More Info : http://www.quirksmode.org/css/box.html
+*/
+ul.sections > li > div {
+  -moz-box-sizing: border-box;    /* firefox */
+  -ms-box-sizing: border-box;     /* ie */
+  -webkit-box-sizing: border-box; /* webkit */
+  -khtml-box-sizing: border-box;  /* konqueror */
+  box-sizing: border-box;         /* css3 */
+}
+
+
+/*---------------------- Jump Page -----------------------------*/
+#jump_to, #jump_page {
+  margin: 0;
+  background: white;
+  -webkit-box-shadow: 0 0 25px #777; -moz-box-shadow: 0 0 25px #777;
+  -webkit-border-bottom-left-radius: 5px; -moz-border-radius-bottomleft: 5px;
+  font: 16px Arial;
+  cursor: pointer;
+  text-align: right;
+  list-style: none;
+}
+
+#jump_to a {
+  text-decoration: none;
+}
+
+#jump_to a.large {
+  display: none;
+}
+#jump_to a.small {
+  font-size: 22px;
+  font-weight: bold;
+  color: #676767;
+}
+
+#jump_to, #jump_wrapper {
+  position: fixed;
+  right: 0; top: 0;
+  padding: 10px 15px;
+  margin:0;
+}
+
+#jump_wrapper {
+  display: none;
+  padding:0;
+}
+
+#jump_to:hover #jump_wrapper {
+  display: block;
+}
+
+#jump_page_wrapper{
+  position: fixed;
+  right: 0;
+  top: 0;
+  bottom: 0;
+}
+
+#jump_page {
+  padding: 5px 0 3px;
+  margin: 0 0 25px 25px;
+  max-height: 100%;
+  overflow: auto;
+}
+
+#jump_page .source {
+  display: block;
+  padding: 15px;
+  text-decoration: none;
+  border-top: 1px solid #eee;
+}
+
+#jump_page .source:hover {
+  background: #f5f5ff;
+}
+
+#jump_page .source:first-child {
+}
+
+/*---------------------- Low resolutions (> 320px) ---------------------*/
+@media only screen and (min-width: 320px) {
+  .pilwrap { display: none; }
+
+  ul.sections > li > div {
+    display: block;
+    padding:5px 10px 0 10px;
+  }
+
+  ul.sections > li > div.annotation ul, ul.sections > li > div.annotation ol {
+    padding-left: 30px;
+  }
+
+  ul.sections > li > div.content {
+    overflow-x:auto;
+    -webkit-box-shadow: inset 0 0 5px #e5e5ee;
+    box-shadow: inset 0 0 5px #e5e5ee;
+    border: 1px solid #dedede;
+    margin:5px 10px 5px 10px;
+    padding-bottom: 5px;
+  }
+
+  ul.sections > li > div.annotation pre {
+    margin: 7px 0 7px;
+    padding-left: 15px;
+  }
+
+  ul.sections > li > div.annotation p tt, .annotation code {
+    background: #f8f8ff;
+    border: 1px solid #dedede;
+    font-size: 12px;
+    padding: 0 0.2em;
+  }
+}
+
+/*----------------------  (> 481px) ---------------------*/
+@media only screen and (min-width: 481px) {
+  #container {
+    position: relative;
+  }
+  body {
+    background-color: #F5F5FF;
+    font-size: 15px;
+    line-height: 21px;
+  }
+  pre, tt, code {
+    line-height: 18px;
+  }
+  p, ul, ol {
+    margin: 0 0 15px;
+  }
+
+
+  #jump_to {
+    padding: 5px 10px;
+  }
+  #jump_wrapper {
+    padding: 0;
+  }
+  #jump_to, #jump_page {
+    font: 10px Arial;
+    text-transform: uppercase;
+  }
+  #jump_page .source {
+    padding: 5px 10px;
+  }
+  #jump_to a.large {
+    display: inline-block;
+  }
+  #jump_to a.small {
+    display: none;
+  }
+
+
+
+  #background {
+    position: absolute;
+    top: 0; bottom: 0;
+    width: 350px;
+    background: #fff;
+    border-right: 1px solid #e5e5ee;
+    z-index: -1;
+  }
+
+  ul.sections > li > div.annotation ul, ul.sections > li > div.annotation ol {
+    padding-left: 40px;
+  }
+
+  ul.sections > li {
+    white-space: nowrap;
+  }
+
+  ul.sections > li > div {
+    display: inline-block;
+  }
+
+  ul.sections > li > div.annotation {
+    max-width: 350px;
+    min-width: 350px;
+    min-height: 5px;
+    padding: 13px;
+    overflow-x: hidden;
+    white-space: normal;
+    vertical-align: top;
+    text-align: left;
+  }
+  ul.sections > li > div.annotation pre {
+    margin: 15px 0 15px;
+    padding-left: 15px;
+  }
+
+  ul.sections > li > div.content {
+    padding: 13px;
+    vertical-align: top;
+    border: none;
+    -webkit-box-shadow: none;
+    box-shadow: none;
+  }
+
+  .pilwrap {
+    position: relative;
+    display: inline;
+  }
+
+  .pilcrow {
+    font: 12px Arial;
+    text-decoration: none;
+    color: #454545;
+    position: absolute;
+    top: 3px; left: -20px;
+    padding: 1px 2px;
+    opacity: 0;
+    -webkit-transition: opacity 0.2s linear;
+  }
+    .for-h1 .pilcrow {
+      top: 47px;
+    }
+    .for-h2 .pilcrow, .for-h3 .pilcrow, .for-h4 .pilcrow {
+      top: 35px;
+    }
+
+  ul.sections > li > div.annotation:hover .pilcrow {
+    opacity: 1;
+  }
+}
+
+/*---------------------- (> 1025px) ---------------------*/
+@media only screen and (min-width: 1025px) {
+
+  body {
+    font-size: 16px;
+    line-height: 24px;
+  }
+
+  #background {
+    width: 525px;
+  }
+  ul.sections > li > div.annotation {
+    max-width: 525px;
+    min-width: 525px;
+    padding: 10px 25px 1px 50px;
+  }
+  ul.sections > li > div.content {
+    padding: 9px 15px 16px 25px;
+  }
+}
+
+/*---------------------- Syntax Highlighting -----------------------------*/
+
+td.linenos { background-color: #f0f0f0; padding-right: 10px; }
+span.lineno { background-color: #f0f0f0; padding: 0 5px 0 5px; }
+/*
+
+github.com style (c) Vasily Polovnyov <vast@whiteants.net>
+
+*/
+
+pre code {
+  display: block; padding: 0.5em;
+  color: #000;
+  background: #f8f8ff
+}
+
+pre .hljs-comment,
+pre .hljs-template_comment,
+pre .hljs-diff .hljs-header,
+pre .hljs-javadoc {
+  color: #408080;
+  font-style: italic
+}
+
+pre .hljs-keyword,
+pre .hljs-assignment,
+pre .hljs-literal,
+pre .hljs-css .hljs-rule .hljs-keyword,
+pre .hljs-winutils,
+pre .hljs-javascript .hljs-title,
+pre .hljs-lisp .hljs-title,
+pre .hljs-subst {
+  color: #954121;
+  /*font-weight: bold*/
+}
+
+pre .hljs-number,
+pre .hljs-hexcolor {
+  color: #40a070
+}
+
+pre .hljs-string,
+pre .hljs-tag .hljs-value,
+pre .hljs-phpdoc,
+pre .hljs-tex .hljs-formula {
+  color: #219161;
+}
+
+pre .hljs-title,
+pre .hljs-id {
+  color: #19469D;
+}
+pre .hljs-params {
+  color: #00F;
+}
+
+pre .hljs-javascript .hljs-title,
+pre .hljs-lisp .hljs-title,
+pre .hljs-subst {
+  font-weight: normal
+}
+
+pre .hljs-class .hljs-title,
+pre .hljs-haskell .hljs-label,
+pre .hljs-tex .hljs-command {
+  color: #458;
+  font-weight: bold
+}
+
+pre .hljs-tag,
+pre .hljs-tag .hljs-title,
+pre .hljs-rules .hljs-property,
+pre .hljs-django .hljs-tag .hljs-keyword {
+  color: #000080;
+  font-weight: normal
+}
+
+pre .hljs-attribute,
+pre .hljs-variable,
+pre .hljs-instancevar,
+pre .hljs-lisp .hljs-body {
+  color: #008080
+}
+
+pre .hljs-regexp {
+  color: #B68
+}
+
+pre .hljs-class {
+  color: #458;
+  font-weight: bold
+}
+
+pre .hljs-symbol,
+pre .hljs-ruby .hljs-symbol .hljs-string,
+pre .hljs-ruby .hljs-symbol .hljs-keyword,
+pre .hljs-ruby .hljs-symbol .hljs-keymethods,
+pre .hljs-lisp .hljs-keyword,
+pre .hljs-tex .hljs-special,
+pre .hljs-input_number {
+  color: #990073
+}
+
+pre .hljs-builtin,
+pre .hljs-constructor,
+pre .hljs-built_in,
+pre .hljs-lisp .hljs-title {
+  color: #0086b3
+}
+
+pre .hljs-preprocessor,
+pre .hljs-pi,
+pre .hljs-doctype,
+pre .hljs-shebang,
+pre .hljs-cdata {
+  color: #999;
+  font-weight: bold
+}
+
+pre .hljs-deletion {
+  background: #fdd
+}
+
+pre .hljs-addition {
+  background: #dfd
+}
+
+pre .hljs-diff .hljs-change {
+  background: #0086b3
+}
+
+pre .hljs-chunk {
+  color: #aaa
+}
+
+pre .hljs-tex .hljs-formula {
+  opacity: 0.5;
+}

examples/html/public/stylesheets/normalize.css

@@ -0,0 +1,375 @@
+/*! normalize.css v2.0.1 | MIT License | git.io/normalize */
+
+/* ==========================================================================
+   HTML5 display definitions
+   ========================================================================== */
+
+/*
+ * Corrects `block` display not defined in IE 8/9.
+ */
+
+article,
+aside,
+details,
+figcaption,
+figure,
+footer,
+header,
+hgroup,
+nav,
+section,
+summary {
+    display: block;
+}
+
+/*
+ * Corrects `inline-block` display not defined in IE 8/9.
+ */
+
+audio,
+canvas,
+video {
+    display: inline-block;
+}
+
+/*
+ * Prevents modern browsers from displaying `audio` without controls.
+ * Remove excess height in iOS 5 devices.
+ */
+
+audio:not([controls]) {
+    display: none;
+    height: 0;
+}
+
+/*
+ * Addresses styling for `hidden` attribute not present in IE 8/9.
+ */
+
+[hidden] {
+    display: none;
+}
+
+/* ==========================================================================
+   Base
+   ========================================================================== */
+
+/*
+ * 1. Sets default font family to sans-serif.
+ * 2. Prevents iOS text size adjust after orientation change, without disabling
+ *    user zoom.
+ */
+
+html {
+    font-family: sans-serif; /* 1 */
+    -webkit-text-size-adjust: 100%; /* 2 */
+    -ms-text-size-adjust: 100%; /* 2 */
+}
+
+/*
+ * Removes default margin.
+ */
+
+body {
+    margin: 0;
+}
+
+/* ==========================================================================
+   Links
+   ========================================================================== */
+
+/*
+ * Addresses `outline` inconsistency between Chrome and other browsers.
+ */
+
+a:focus {
+    outline: thin dotted;
+}
+
+/*
+ * Improves readability when focused and also mouse hovered in all browsers.
+ */
+
+a:active,
+a:hover {
+    outline: 0;
+}
+
+/* ==========================================================================
+   Typography
+   ========================================================================== */
+
+/*
+ * Addresses `h1` font sizes within `section` and `article` in Firefox 4+,
+ * Safari 5, and Chrome.
+ */
+
+h1 {
+    font-size: 2em;
+}
+
+/*
+ * Addresses styling not present in IE 8/9, Safari 5, and Chrome.
+ */
+
+abbr[title] {
+    border-bottom: 1px dotted;
+}
+
+/*
+ * Addresses style set to `bolder` in Firefox 4+, Safari 5, and Chrome.
+ */
+
+b,
+strong {
+    font-weight: bold;
+}
+
+/*
+ * Addresses styling not present in Safari 5 and Chrome.
+ */
+
+dfn {
+    font-style: italic;
+}
+
+/*
+ * Addresses styling not present in IE 8/9.
+ */
+
+mark {
+    background: #ff0;
+    color: #000;
+}
+
+
+/*
+ * Corrects font family set oddly in Safari 5 and Chrome.
+ */
+
+code,
+kbd,
+pre,
+samp {
+    font-family: monospace, serif;
+    font-size: 1em;
+}
+
+/*
+ * Improves readability of pre-formatted text in all browsers.
+ */
+
+pre {
+    white-space: pre;
+    white-space: pre-wrap;
+    word-wrap: break-word;
+}
+
+/*
+ * Sets consistent quote types.
+ */
+
+q {
+    quotes: "\201C" "\201D" "\2018" "\2019";
+}
+
+/*
+ * Addresses inconsistent and variable font size in all browsers.
+ */
+
+small {
+    font-size: 80%;
+}
+
+/*
+ * Prevents `sub` and `sup` affecting `line-height` in all browsers.
+ */
+
+sub,
+sup {
+    font-size: 75%;
+    line-height: 0;
+    position: relative;
+    vertical-align: baseline;
+}
+
+sup {
+    top: -0.5em;
+}
+
+sub {
+    bottom: -0.25em;
+}
+
+/* ==========================================================================
+   Embedded content
+   ========================================================================== */
+
+/*
+ * Removes border when inside `a` element in IE 8/9.
+ */
+
+img {
+    border: 0;
+}
+
+/*
+ * Corrects overflow displayed oddly in IE 9.
+ */
+
+svg:not(:root) {
+    overflow: hidden;
+}
+
+/* ==========================================================================
+   Figures
+   ========================================================================== */
+
+/*
+ * Addresses margin not present in IE 8/9 and Safari 5.
+ */
+
+figure {
+    margin: 0;
+}
+
+/* ==========================================================================
+   Forms
+   ========================================================================== */
+
+/*
+ * Define consistent border, margin, and padding.
+ */
+
+fieldset {
+    border: 1px solid #c0c0c0;
+    margin: 0 2px;
+    padding: 0.35em 0.625em 0.75em;
+}
+
+/*
+ * 1. Corrects color not being inherited in IE 8/9.
+ * 2. Remove padding so people aren't caught out if they zero out fieldsets.
+ */
+
+legend {
+    border: 0; /* 1 */
+    padding: 0; /* 2 */
+}
+
+/*
+ * 1. Corrects font family not being inherited in all browsers.
+ * 2. Corrects font size not being inherited in all browsers.
+ * 3. Addresses margins set differently in Firefox 4+, Safari 5, and Chrome
+ */
+
+button,
+input,
+select,
+textarea {
+    font-family: inherit; /* 1 */
+    font-size: 100%; /* 2 */
+    margin: 0; /* 3 */
+}
+
+/*
+ * Addresses Firefox 4+ setting `line-height` on `input` using `!important` in
+ * the UA stylesheet.
+ */
+
+button,
+input {
+    line-height: normal;
+}
+
+/*
+ * 1. Avoid the WebKit bug in Android 4.0.* where (2) destroys native `audio`
+ *    and `video` controls.
+ * 2. Corrects inability to style clickable `input` types in iOS.
+ * 3. Improves usability and consistency of cursor style between image-type
+ *    `input` and others.
+ */
+
+button,
+html input[type="button"], /* 1 */
+input[type="reset"],
+input[type="submit"] {
+    -webkit-appearance: button; /* 2 */
+    cursor: pointer; /* 3 */
+}
+
+/*
+ * Re-set default cursor for disabled elements.
+ */
+
+button[disabled],
+input[disabled] {
+    cursor: default;
+}
+
+/*
+ * 1. Addresses box sizing set to `content-box` in IE 8/9.
+ * 2. Removes excess padding in IE 8/9.
+ */
+
+input[type="checkbox"],
+input[type="radio"] {
+    box-sizing: border-box; /* 1 */
+    padding: 0; /* 2 */
+}
+
+/*
+ * 1. Addresses `appearance` set to `searchfield` in Safari 5 and Chrome.
+ * 2. Addresses `box-sizing` set to `border-box` in Safari 5 and Chrome
+ *    (include `-moz` to future-proof).
+ */
+
+input[type="search"] {
+    -webkit-appearance: textfield; /* 1 */
+    -moz-box-sizing: content-box;
+    -webkit-box-sizing: content-box; /* 2 */
+    box-sizing: content-box;
+}
+
+/*
+ * Removes inner padding and search cancel button in Safari 5 and Chrome
+ * on OS X.
+ */
+
+input[type="search"]::-webkit-search-cancel-button,
+input[type="search"]::-webkit-search-decoration {
+    -webkit-appearance: none;
+}
+
+/*
+ * Removes inner padding and border in Firefox 4+.
+ */
+
+button::-moz-focus-inner,
+input::-moz-focus-inner {
+    border: 0;
+    padding: 0;
+}
+
+/*
+ * 1. Removes default vertical scrollbar in IE 8/9.
+ * 2. Improves readability and alignment in all browsers.
+ */
+
+textarea {
+    overflow: auto; /* 1 */
+    vertical-align: top; /* 2 */
+}
+
+/* ==========================================================================
+   Tables
+   ========================================================================== */
+
+/*
+ * Remove most spacing between table cells.
+ */
+
+table {
+    border-collapse: collapse;
+    border-spacing: 0;
+}

examples/html/simple_search.html

@@ -0,0 +1,542 @@
+<!DOCTYPE html>
+
+<html>
+<head>
+  <title>simple_search.rs</title>
+  <meta http-equiv="content-type" content="text/html; charset=UTF-8">
+  <meta name="viewport" content="width=device-width, target-densitydpi=160dpi, initial-scale=1.0; maximum-scale=1.0; user-scalable=0;">
+  <link rel="stylesheet" media="all" href="docco.css" />
+</head>
+<body>
+  <div id="container">
+    <div id="background"></div>
+    
+    <ul class="sections">
+        
+          <li id="title">
+              <div class="annotation">
+                  <h1>simple_search.rs</h1>
+              </div>
+          </li>
+        
+        
+        
+        <li id="section-1">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-1">&#182;</a>
+              </div>
+              
+            </div>
+            
+            <div class="content"><div class='highlight'><pre><span class="hljs-keyword">extern</span> <span class="hljs-keyword">crate</span> tantivy;
+<span class="hljs-keyword">extern</span> <span class="hljs-keyword">crate</span> tempdir;
+
+<span class="hljs-meta">#[macro_use]</span>
+<span class="hljs-keyword">extern</span> <span class="hljs-keyword">crate</span> serde_json;
+
+<span class="hljs-keyword">use</span> std::path::Path;
+<span class="hljs-keyword">use</span> tempdir::TempDir;
+<span class="hljs-keyword">use</span> tantivy::Index;
+<span class="hljs-keyword">use</span> tantivy::schema::*;
+<span class="hljs-keyword">use</span> tantivy::collector::TopCollector;
+<span class="hljs-keyword">use</span> tantivy::query::QueryParser;
+
+<span class="hljs-function"><span class="hljs-keyword">fn</span> <span class="hljs-title">main</span></span>() {</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-2">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-2">&#182;</a>
+              </div>
+              <p>Let’s create a temporary directory for the
+sake of this example</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">if</span> <span class="hljs-keyword">let</span> <span class="hljs-literal">Ok</span>(dir) = TempDir::new(<span class="hljs-string">"tantivy_example_dir"</span>) {
+        run_example(dir.path()).unwrap();
+        dir.close().unwrap();
+    }
+}
+
+
+<span class="hljs-function"><span class="hljs-keyword">fn</span> <span class="hljs-title">run_example</span></span>(index_path: &amp;Path) -&gt; tantivy::<span class="hljs-built_in">Result</span>&lt;()&gt; {</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-3">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-3">&#182;</a>
+              </div>
+              <h1 id="defining-the-schema">Defining the schema</h1>
+<p>The Tantivy index requires a very strict schema.
+The schema declares which fields are in the index,
+and for each field, its type and “the way it should
+be indexed”.</p>
+
+            </div>
+            
+        </li>
+        
+        
+        <li id="section-4">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-4">&#182;</a>
+              </div>
+              <p>first we need to define a schema …</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> schema_builder = SchemaBuilder::<span class="hljs-keyword">default</span>();</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-5">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-5">&#182;</a>
+              </div>
+              <p>Our first field is title.
+We want full-text search for it, and we also want 
+to be able to retrieve the document after the search.</p>
+<p>TEXT | STORED is some syntactic sugar to describe
+that.</p>
+<p><code>TEXT</code> means the field should be tokenized and indexed,
+along with its term frequency and term positions.</p>
+<p><code>STORED</code> means that the field will also be saved
+in a compressed, row-oriented key-value store.
+This store is useful to reconstruct the
+documents that were selected during the search phase.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    schema_builder.add_text_field(<span class="hljs-string">"title"</span>, TEXT | STORED);</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-6">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-6">&#182;</a>
+              </div>
+              <p>Our second field is body.
+We want full-text search for it, but we do not 
+need to be able to be able to retrieve it
+for our application. </p>
+<p>We can make our index lighter and 
+by omitting <code>STORED</code> flag.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    schema_builder.add_text_field(<span class="hljs-string">"body"</span>, TEXT);
+
+    <span class="hljs-keyword">let</span> schema = schema_builder.build();</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-7">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-7">&#182;</a>
+              </div>
+              <h1 id="indexing-documents">Indexing documents</h1>
+<p>Let’s create a brand new index.</p>
+<p>This will actually just save a meta.json
+with our schema in the directory.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> index = Index::create(index_path, schema.clone())?;</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-8">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-8">&#182;</a>
+              </div>
+              <p>To insert document we need an index writer.
+There must be only one writer at a time.
+This single <code>IndexWriter</code> is already
+multithreaded.</p>
+<p>Here we use a buffer of 50MB per thread. Using a bigger
+heap for the indexer can increase its throughput.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> index_writer = index.writer(<span class="hljs-number">50_000_000</span>)?;</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-9">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-9">&#182;</a>
+              </div>
+              <p>Let’s index our documents!
+We first need a handle on the title and the body field.</p>
+
+            </div>
+            
+        </li>
+        
+        
+        <li id="section-10">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-10">&#182;</a>
+              </div>
+              <h3 id="create-a-document-manually-">Create a document “manually”.</h3>
+<p>We can create a document manually, by setting the fields
+one by one in a Document object.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> title = schema.get_field(<span class="hljs-string">"title"</span>).unwrap();
+    <span class="hljs-keyword">let</span> body = schema.get_field(<span class="hljs-string">"body"</span>).unwrap();
+
+    <span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> old_man_doc = Document::<span class="hljs-keyword">default</span>();
+    old_man_doc.add_text(title, <span class="hljs-string">"The Old Man and the Sea"</span>);
+    old_man_doc.add_text(
+        body,
+        <span class="hljs-string">"He was an old man who fished alone in a skiff in the Gulf Stream and \
+                          he had gone eighty-four days now without taking a fish."</span>,
+    );</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-11">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-11">&#182;</a>
+              </div>
+              <p>… and add it to the <code>IndexWriter</code>.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    index_writer.add_document(old_man_doc);</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-12">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-12">&#182;</a>
+              </div>
+              <h3 id="create-a-document-directly-from-json-">Create a document directly from json.</h3>
+<p>Alternatively, we can use our schema to parse a
+document object directly from json.
+The document is a string, but we use the <code>json</code> macro
+from <code>serde_json</code> for the convenience of multi-line support.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> json = json!({
+       <span class="hljs-string">"title"</span>: <span class="hljs-string">"Of Mice and Men"</span>,
+       <span class="hljs-string">"body"</span>: <span class="hljs-string">"A few miles south of Soledad, the Salinas River drops in close to the hillside \
+                bank and runs deep and green. The water is warm too, for it has slipped twinkling \
+                over the yellow sands in the sunlight before reaching the narrow pool. On one \
+                side of the river the golden foothill slopes curve up to the strong and rocky \
+                Gabilan Mountains, but on the valley side the water is lined with trees—willows \
+                fresh and green with every spring, carrying in their lower leaf junctures the \
+                debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
+                limbs and branches that arch over the pool"</span>
+    });
+    <span class="hljs-keyword">let</span> mice_and_men_doc = schema.parse_document(&amp;json.to_string())?;
+
+    index_writer.add_document(mice_and_men_doc);</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-13">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-13">&#182;</a>
+              </div>
+              <p>Multi-valued field are allowed, they are
+expressed in JSON by an array.
+The following document has two titles.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> json = json!({
+       <span class="hljs-string">"title"</span>: [<span class="hljs-string">"Frankenstein"</span>, <span class="hljs-string">"The Modern Prometheus"</span>],
+       <span class="hljs-string">"body"</span>: <span class="hljs-string">"You will rejoice to hear that no disaster has accompanied the commencement of an \
+                enterprise which you have regarded with such evil forebodings.  I arrived here \
+                yesterday, and my first task is to assure my dear sister of my welfare and \
+                increasing confidence in the success of my undertaking."</span>
+    });
+    <span class="hljs-keyword">let</span> frankenstein_doc = schema.parse_document(&amp;json.to_string())?;
+
+    index_writer.add_document(frankenstein_doc);</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-14">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-14">&#182;</a>
+              </div>
+              <p>This is an example, so we will only index 3 documents
+here. You can check out tantivy’s tutorial to index
+the English wikipedia. Tantivy’s indexing is rather fast.
+Indexing 5 million articles of the English wikipedia takes
+around 4 minutes on my computer!</p>
+
+            </div>
+            
+        </li>
+        
+        
+        <li id="section-15">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-15">&#182;</a>
+              </div>
+              <h3 id="committing">Committing</h3>
+<p>At this point our documents are not searchable.</p>
+<p>We need to call .commit() explicitly to force the
+index_writer to finish processing the documents in the queue,
+flush the current index to the disk, and advertise
+the existence of new documents.</p>
+<p>This call is blocking.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    index_writer.commit()?;</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-16">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-16">&#182;</a>
+              </div>
+              <p>If <code>.commit()</code> returns correctly, then all of the
+documents that have been added are guaranteed to be
+persistently indexed.</p>
+<p>In the scenario of a crash or a power failure,
+tantivy behaves as if has rolled back to its last
+commit.</p>
+
+            </div>
+            
+        </li>
+        
+        
+        <li id="section-17">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-17">&#182;</a>
+              </div>
+              <h1 id="searching">Searching</h1>
+<p>Let’s search our index. Start by reloading
+searchers in the index. This should be done
+after every commit().</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    index.load_searchers()?;</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-18">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-18">&#182;</a>
+              </div>
+              <p>Afterwards create one (or more) searchers.</p>
+<p>You should create a searcher
+every time you start a “search query”.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> searcher = index.searcher();</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-19">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-19">&#182;</a>
+              </div>
+              <p>The query parser can interpret human queries.
+Here, if the user does not specify which
+field they want to search, tantivy will search
+in both title and body.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> query_parser = QueryParser::for_index(index, <span class="hljs-built_in">vec!</span>[title, body]);</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-20">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-20">&#182;</a>
+              </div>
+              <p>QueryParser may fail if the query is not in the right
+format. For user facing applications, this can be a problem.
+A ticket has been opened regarding this problem.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> query = query_parser.parse_query(<span class="hljs-string">"sea whale"</span>)?;</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-21">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-21">&#182;</a>
+              </div>
+              <p>A query defines a set of documents, as
+well as the way they should be scored.</p>
+<p>A query created by the query parser is scored according
+to a metric called Tf-Idf, and will consider
+any document matching at least one of our terms.</p>
+
+            </div>
+            
+        </li>
+        
+        
+        <li id="section-22">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-22">&#182;</a>
+              </div>
+              <h3 id="collectors">Collectors</h3>
+<p>We are not interested in all of the documents but
+only in the top 10. Keeping track of our top 10 best documents
+is the role of the TopCollector.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> top_collector = TopCollector::with_limit(<span class="hljs-number">10</span>);</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-23">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-23">&#182;</a>
+              </div>
+              <p>We can now perform our query.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    searcher.search(&amp;*query, &amp;<span class="hljs-keyword">mut</span> top_collector)?;</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-24">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-24">&#182;</a>
+              </div>
+              <p>Our top collector now contains the 10
+most relevant doc ids…</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    <span class="hljs-keyword">let</span> doc_addresses = top_collector.docs();</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-25">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-25">&#182;</a>
+              </div>
+              <p>The actual documents still need to be
+retrieved from Tantivy’s store.</p>
+<p>Since the body field was not configured as stored,
+the document returned will only contain
+a title.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>
+    <span class="hljs-keyword">for</span> doc_address <span class="hljs-keyword">in</span> doc_addresses {
+        <span class="hljs-keyword">let</span> retrieved_doc = searcher.doc(&amp;doc_address)?;
+        <span class="hljs-built_in">println!</span>(<span class="hljs-string">"{}"</span>, schema.to_json(&amp;retrieved_doc));
+    }</pre></div></div>
+            
+        </li>
+        
+        
+        <li id="section-26">
+            <div class="annotation">
+              
+              <div class="pilwrap ">
+                <a class="pilcrow" href="#section-26">&#182;</a>
+              </div>
+              <p>Wait for indexing and merging threads to shut down.
+Usually this isn’t needed, but in <code>main</code> we try to
+delete the temporary directory and that fails on
+Windows if the files are still open.</p>
+
+            </div>
+            
+            <div class="content"><div class='highlight'><pre>    index_writer.wait_merging_threads()?;
+
+    <span class="hljs-literal">Ok</span>(())
+}</pre></div></div>
+            
+        </li>
+        
+    </ul>
+  </div>
+</body>
+</html>

examples/integer_range_search.rs

@@ -1,39 +0,0 @@
-// # Searching a range on an indexed int field.
-//
-// Below is an example of creating an indexed integer field in your schema
-// You can use RangeQuery to get a Count of all occurrences in a given range.
-use tantivy::collector::Count;
-use tantivy::query::RangeQuery;
-use tantivy::schema::{Schema, INDEXED};
-use tantivy::{doc, Index, Result};
-
-fn run() -> Result<()> {
-    // For the sake of simplicity, this schema will only have 1 field
-    let mut schema_builder = Schema::builder();
-
-    // `INDEXED` is a short-hand to indicate that our field should be "searchable".
-    let year_field = schema_builder.add_u64_field("year", INDEXED);
-    let schema = schema_builder.build();
-    let index = Index::create_in_ram(schema);
-    let reader = index.reader()?;
-    {
-        let mut index_writer = index.writer_with_num_threads(1, 6_000_000)?;
-        for year in 1950u64..2019u64 {
-            index_writer.add_document(doc!(year_field => year));
-        }
-        index_writer.commit()?;
-        // The index will be a range of years
-    }
-    reader.reload()?;
-    let searcher = reader.searcher();
-    // The end is excluded i.e. here we are searching up to 1969
-    let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960..1970);
-    // Uses a Count collector to sum the total number of docs in the range
-    let num_60s_books = searcher.search(&docs_in_the_sixties, &Count)?;
-    assert_eq!(num_60s_books, 10);
-    Ok(())
-}
-
-fn main() {
-    run().unwrap()
-}

examples/iterating_docs_and_positions.rs

@@ -1,135 +0,0 @@
-// # Iterating docs and positions.
-//
-// At its core of tantivy, relies on a data structure
-// called an inverted index.
-//
-// This example shows how to manually iterate through
-// the list of documents containing a term, getting
-// its term frequency, and accessing its positions.
-
-// ---
-// Importing tantivy...
-use tantivy::schema::*;
-use tantivy::{doc, DocSet, Index, Postings, TERMINATED};
-
-fn main() -> tantivy::Result<()> {
-    // We first create a schema for the sake of the
-    // example. Check the `basic_search` example for more information.
-    let mut schema_builder = Schema::builder();
-
-    // For this example, we need to make sure to index positions for our title
-    // field. `TEXT` precisely does this.
-    let title = schema_builder.add_text_field("title", TEXT | STORED);
-    let schema = schema_builder.build();
-
-    let index = Index::create_in_ram(schema);
-
-    let mut index_writer = index.writer_with_num_threads(1, 50_000_000)?;
-    index_writer.add_document(doc!(title => "The Old Man and the Sea"));
-    index_writer.add_document(doc!(title => "Of Mice and Men"));
-    index_writer.add_document(doc!(title => "The modern Promotheus"));
-    index_writer.commit()?;
-
-    let reader = index.reader()?;
-
-    let searcher = reader.searcher();
-
-    // A tantivy index is actually a collection of segments.
-    // Similarly, a searcher just wraps a list `segment_reader`.
-    //
-    // (Because we indexed a very small number of documents over one thread
-    // there is actually only one segment here, but let's iterate through the list
-    // anyway)
-    for segment_reader in searcher.segment_readers() {
-        // A segment contains different data structure.
-        // Inverted index stands for the combination of
-        // - the term dictionary
-        // - the inverted lists associated to each terms and their positions
-        let inverted_index = segment_reader.inverted_index(title)?;
-
-        // A `Term` is a text token associated with a field.
-        // Let's go through all docs containing the term `title:the` and access their position
-        let term_the = Term::from_field_text(title, "the");
-
-        // This segment posting object is like a cursor over the documents matching the term.
-        // The `IndexRecordOption` arguments tells tantivy we will be interested in both term frequencies
-        // and positions.
-        //
-        // If you don't need all this information, you may get better performance by decompressing less
-        // information.
-        if let Some(mut segment_postings) =
-            inverted_index.read_postings(&term_the, IndexRecordOption::WithFreqsAndPositions)?
-        {
-            // this buffer will be used to request for positions
-            let mut positions: Vec<u32> = Vec::with_capacity(100);
-            let mut doc_id = segment_postings.doc();
-            while doc_id != TERMINATED {
-                // This MAY contains deleted documents as well.
-                if segment_reader.is_deleted(doc_id) {
-                    doc_id = segment_postings.advance();
-                    continue;
-                }
-
-                // the number of time the term appears in the document.
-                let term_freq: u32 = segment_postings.term_freq();
-                // accessing positions is slightly expensive and lazy, do not request
-                // for them if you don't need them for some documents.
-                segment_postings.positions(&mut positions);
-
-                // By definition we should have `term_freq` positions.
-                assert_eq!(positions.len(), term_freq as usize);
-
-                // This prints:
-                // ```
-                // Doc 0: TermFreq 2: [0, 4]
-                // Doc 2: TermFreq 1: [0]
-                // ```
-                println!("Doc {}: TermFreq {}: {:?}", doc_id, term_freq, positions);
-                doc_id = segment_postings.advance();
-            }
-        }
-    }
-
-    // A `Term` is a text token associated with a field.
-    // Let's go through all docs containing the term `title:the` and access their position
-    let term_the = Term::from_field_text(title, "the");
-
-    // Some other powerful operations (especially `.skip_to`) may be useful to consume these
-    // posting lists rapidly.
-    // You can check for them in the [`DocSet`](https://docs.rs/tantivy/~0/tantivy/trait.DocSet.html) trait
-    // and the [`Postings`](https://docs.rs/tantivy/~0/tantivy/trait.Postings.html) trait
-
-    // Also, for some VERY specific high performance use case like an OLAP analysis of logs,
-    // you can get better performance by accessing directly the blocks of doc ids.
-    for segment_reader in searcher.segment_readers() {
-        // A segment contains different data structure.
-        // Inverted index stands for the combination of
-        // - the term dictionary
-        // - the inverted lists associated to each terms and their positions
-        let inverted_index = segment_reader.inverted_index(title)?;
-
-        // This segment posting object is like a cursor over the documents matching the term.
-        // The `IndexRecordOption` arguments tells tantivy we will be interested in both term frequencies
-        // and positions.
-        //
-        // If you don't need all this information, you may get better performance by decompressing less
-        // information.
-        if let Some(mut block_segment_postings) =
-            inverted_index.read_block_postings(&term_the, IndexRecordOption::Basic)?
-        {
-            loop {
-                let docs = block_segment_postings.docs();
-                if docs.is_empty() {
-                    break;
-                }
-                // Once again these docs MAY contains deleted documents as well.
-                let docs = block_segment_postings.docs();
-                // Prints `Docs [0, 2].`
-                println!("Docs {:?}", docs);
-                block_segment_postings.advance();
-            }
-        }
-    }
-
-    Ok(())
-}

examples/multiple_producer.rs

@@ -1,100 +0,0 @@
-// # Indexing from different threads.
-//
-// It is fairly common to have to index from different threads.
-// Tantivy forbids to create more than one `IndexWriter` at a time.
-//
-// This `IndexWriter` itself has its own multithreaded layer, so managing your own
-// indexing threads will not help. However, it can still be useful for some applications.
-//
-// For instance, if preparing documents to send to tantivy before indexing is the bottleneck of
-// your application, it is reasonable to have multiple threads.
-//
-// Another very common reason to want to index from multiple threads, is implementing a webserver
-// with CRUD capabilities. The server framework will most likely handle request from
-// different threads.
-//
-// The recommended way to address both of these use case is to wrap your `IndexWriter` into a
-// `Arc<RwLock<IndexWriter>>`.
-//
-// While this is counterintuitive, adding and deleting documents do not require mutability
-// over the `IndexWriter`, so several threads will be able to do this operation concurrently.
-//
-// The example below does not represent an actual real-life use case (who would spawn thread to
-// index a single document?), but aims at demonstrating the mechanism that makes indexing
-// from several threads possible.
-
-// ---
-// Importing tantivy...
-use std::sync::{Arc, RwLock};
-use std::thread;
-use std::time::Duration;
-use tantivy::schema::{Schema, STORED, TEXT};
-use tantivy::{doc, Index, IndexWriter, Opstamp};
-
-fn main() -> tantivy::Result<()> {
-    // # Defining the schema
-    let mut schema_builder = Schema::builder();
-    let title = schema_builder.add_text_field("title", TEXT | STORED);
-    let body = schema_builder.add_text_field("body", TEXT);
-    let schema = schema_builder.build();
-
-    let index = Index::create_in_ram(schema);
-    let index_writer: Arc<RwLock<IndexWriter>> = Arc::new(RwLock::new(index.writer(50_000_000)?));
-
-    // # First indexing thread.
-    let index_writer_clone_1 = index_writer.clone();
-    thread::spawn(move || {
-        // we index 100 times the document... for the sake of the example.
-        for i in 0..100 {
-            let opstamp = index_writer_clone_1
-                .read().unwrap() //< A read lock is sufficient here.
-                .add_document(
-                    doc!(
-                        title => "Of Mice and Men",
-                        body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
-                        bank and runs deep and green. The water is warm too, for it has slipped twinkling \
-                        over the yellow sands in the sunlight before reaching the narrow pool. On one \
-                        side of the river the golden foothill slopes curve up to the strong and rocky \
-                        Gabilan Mountains, but on the valley side the water is lined with trees—willows \
-                        fresh and green with every spring, carrying in their lower leaf junctures the \
-                        debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
-                        limbs and branches that arch over the pool"
-                    ));
-            println!("add doc {} from thread 1 - opstamp {}", i, opstamp);
-            thread::sleep(Duration::from_millis(20));
-        }
-    });
-
-    // # Second indexing thread.
-    let index_writer_clone_2 = index_writer.clone();
-    // For convenience, tantivy also comes with a macro to
-    // reduce the boilerplate above.
-    thread::spawn(move || {
-        // we index 100 times the document... for the sake of the example.
-        for i in 0..100 {
-            // A read lock is sufficient here.
-            let opstamp = {
-                let index_writer_rlock = index_writer_clone_2.read().unwrap();
-                index_writer_rlock.add_document(doc!(
-                    title => "Manufacturing consent",
-                    body => "Some great book description..."
-                ))
-            };
-            println!("add doc {} from thread 2 - opstamp {}", i, opstamp);
-            thread::sleep(Duration::from_millis(10));
-        }
-    });
-
-    // # In the main thread, we commit 10 times, once every 500ms.
-    for _ in 0..10 {
-        let opstamp: Opstamp = {
-            // Committing or rollbacking on the other hand requires write lock. This will block other threads.
-            let mut index_writer_wlock = index_writer.write().unwrap();
-            index_writer_wlock.commit().unwrap()
-        };
-        println!("committed with opstamp {}", opstamp);
-        thread::sleep(Duration::from_millis(500));
-    }
-
-    Ok(())
-}

examples/pre_tokenized_text.rs

@@ -1,139 +0,0 @@
-// # Pre-tokenized text example
-//
-// This example shows how to use pre-tokenized text. Sometimes you might
-// want to index and search through text which is already split into
-// tokens by some external tool.
-//
-// In this example we will:
-// - use tantivy tokenizer to create tokens and load them directly into tantivy,
-// - import tokenized text straight from json,
-// - perform a search on documents with pre-tokenized text
-
-use tantivy::collector::{Count, TopDocs};
-use tantivy::query::TermQuery;
-use tantivy::schema::*;
-use tantivy::tokenizer::{PreTokenizedString, SimpleTokenizer, Token, Tokenizer};
-use tantivy::{doc, Index, ReloadPolicy};
-use tempfile::TempDir;
-
-fn pre_tokenize_text(text: &str) -> Vec<Token> {
-    let mut token_stream = SimpleTokenizer.token_stream(text);
-    let mut tokens = vec![];
-    while token_stream.advance() {
-        tokens.push(token_stream.token().clone());
-    }
-    tokens
-}
-
-fn main() -> tantivy::Result<()> {
-    let index_path = TempDir::new()?;
-
-    let mut schema_builder = Schema::builder();
-
-    schema_builder.add_text_field("title", TEXT | STORED);
-    schema_builder.add_text_field("body", TEXT);
-
-    let schema = schema_builder.build();
-
-    let index = Index::create_in_dir(&index_path, schema.clone())?;
-
-    let mut index_writer = index.writer(50_000_000)?;
-
-    // We can create a document manually, by setting the fields
-    // one by one in a Document object.
-    let title = schema.get_field("title").unwrap();
-    let body = schema.get_field("body").unwrap();
-
-    let title_text = "The Old Man and the Sea";
-    let body_text = "He was an old man who fished alone in a skiff in the Gulf Stream";
-
-    // Content of our first document
-    // We create `PreTokenizedString` which contains original text and vector of tokens
-    let title_tok = PreTokenizedString {
-        text: String::from(title_text),
-        tokens: pre_tokenize_text(title_text),
-    };
-
-    println!(
-        "Original text: \"{}\" and tokens: {:?}",
-        title_tok.text, title_tok.tokens
-    );
-
-    let body_tok = PreTokenizedString {
-        text: String::from(body_text),
-        tokens: pre_tokenize_text(body_text),
-    };
-
-    // Now lets create a document and add our `PreTokenizedString`
-    let old_man_doc = doc!(title => title_tok, body => body_tok);
-
-    // ... now let's just add it to the IndexWriter
-    index_writer.add_document(old_man_doc);
-
-    // Pretokenized text can also be fed as JSON
-    let short_man_json = r#"{
-        "title":[{
-            "text":"The Old Man",
-            "tokens":[
-                {"offset_from":0,"offset_to":3,"position":0,"text":"The","position_length":1},
-                {"offset_from":4,"offset_to":7,"position":1,"text":"Old","position_length":1},
-                {"offset_from":8,"offset_to":11,"position":2,"text":"Man","position_length":1}
-            ]
-        }]
-    }"#;
-
-    let short_man_doc = schema.parse_document(short_man_json)?;
-
-    index_writer.add_document(short_man_doc);
-
-    // Let's commit changes
-    index_writer.commit()?;
-
-    // ... and now is the time to query our index
-
-    let reader = index
-        .reader_builder()
-        .reload_policy(ReloadPolicy::OnCommit)
-        .try_into()?;
-
-    let searcher = reader.searcher();
-
-    // We want to get documents with token "Man", we will use TermQuery to do it
-    // Using PreTokenizedString means the tokens are stored as is avoiding stemming
-    // and lowercasing, which preserves full words in their original form
-    let query = TermQuery::new(
-        Term::from_field_text(title, "Man"),
-        IndexRecordOption::Basic,
-    );
-
-    let (top_docs, count) = searcher
-        .search(&query, &(TopDocs::with_limit(2), Count))
-        .unwrap();
-
-    assert_eq!(count, 2);
-
-    // Now let's print out the results.
-    // Note that the tokens are not stored along with the original text
-    // in the document store
-    for (_score, doc_address) in top_docs {
-        let retrieved_doc = searcher.doc(doc_address)?;
-        println!("Document: {}", schema.to_json(&retrieved_doc));
-    }
-
-    // In contrary to the previous query, when we search for the "man" term we
-    // should get no results, as it's not one of the indexed tokens. SimpleTokenizer
-    // only splits text on whitespace / punctuation.
-
-    let query = TermQuery::new(
-        Term::from_field_text(title, "man"),
-        IndexRecordOption::Basic,
-    );
-
-    let (_top_docs, count) = searcher
-        .search(&query, &(TopDocs::with_limit(2), Count))
-        .unwrap();
-
-    assert_eq!(count, 0);
-
-    Ok(())
-}

examples/simple_search.rs

@@ -1,28 +1,26 @@
-// # Basic Example
-//
-// This example covers the basic functionalities of
-// tantivy.
-//
-// We will :
-// - define our schema
-// - create an index in a directory
-// - index a few documents into our index
-// - search for the best document matching a basic query
-// - retrieve the best document's original content.
+extern crate tantivy;
+extern crate tempdir;
 
-// ---
-// Importing tantivy...
-use tantivy::collector::TopDocs;
-use tantivy::query::QueryParser;
+#[macro_use]
+extern crate serde_json;
+
+use std::path::Path;
+use tempdir::TempDir;
+use tantivy::Index;
 use tantivy::schema::*;
-use tantivy::{doc, Index, ReloadPolicy};
-use tempfile::TempDir;
+use tantivy::collector::TopCollector;
+use tantivy::query::QueryParser;
 
-fn main() -> tantivy::Result<()> {
+fn main() {
     // Let's create a temporary directory for the
     // sake of this example
-    let index_path = TempDir::new()?;
+    if let Ok(dir) = TempDir::new("tantivy_example_dir") {
+        run_example(dir.path()).unwrap();
+        dir.close().unwrap();
+    }
+}
 
+fn run_example(index_path: &Path) -> tantivy::Result<()> {
     // # Defining the schema
     //
     // The Tantivy index requires a very strict schema.
@@ -30,14 +28,14 @@ fn main() -> tantivy::Result<()> {
     // and for each field, its type and "the way it should
     // be indexed".
 
-    // First we need to define a schema ...
-    let mut schema_builder = Schema::builder();
+    // first we need to define a schema ...
+    let mut schema_builder = SchemaBuilder::default();
 
     // Our first field is title.
     // We want full-text search for it, and we also want
     // to be able to retrieve the document after the search.
     //
-    // `TEXT | STORED` is some syntactic sugar to describe
+    // TEXT | STORED is some syntactic sugar to describe
     // that.
     //
     // `TEXT` means the field should be tokenized and indexed,
@@ -45,7 +43,7 @@ fn main() -> tantivy::Result<()> {
     //
     // `STORED` means that the field will also be saved
     // in a compressed, row-oriented key-value store.
-    // This store is useful for reconstructing the
+    // This store is useful to reconstruct the
     // documents that were selected during the search phase.
     schema_builder.add_text_field("title", TEXT | STORED);
 
@@ -54,7 +52,8 @@ fn main() -> tantivy::Result<()> {
     // need to be able to be able to retrieve it
     // for our application.
     //
-    // We can make our index lighter by omitting the `STORED` flag.
+    // We can make our index lighter and
+    // by omitting `STORED` flag.
     schema_builder.add_text_field("body", TEXT);
 
     let schema = schema_builder.build();
@@ -65,22 +64,21 @@ fn main() -> tantivy::Result<()> {
     //
     // This will actually just save a meta.json
     // with our schema in the directory.
-    let index = Index::create_in_dir(&index_path, schema.clone())?;
+    let index = Index::create(index_path, schema.clone())?;
 
-    // To insert a document we will need an index writer.
+    // To insert document we need an index writer.
     // There must be only one writer at a time.
     // This single `IndexWriter` is already
     // multithreaded.
     //
-    // Here we give tantivy a budget of `50MB`.
-    // Using a bigger heap for the indexer may increase
-    // throughput, but 50 MB is already plenty.
+    // Here we use a buffer of 50MB per thread. Using a bigger
+    // heap for the indexer can increase its throughput.
     let mut index_writer = index.writer(50_000_000)?;
 
     // Let's index our documents!
     // We first need a handle on the title and the body field.
 
-    // ### Adding documents
+    // ### Create a document "manually".
     //
     // We can create a document manually, by setting the fields
     // one by one in a Document object.
@@ -98,43 +96,54 @@ fn main() -> tantivy::Result<()> {
     // ... and add it to the `IndexWriter`.
     index_writer.add_document(old_man_doc);
 
-    // For convenience, tantivy also comes with a macro to
-    // reduce the boilerplate above.
-    index_writer.add_document(doc!(
-    title => "Of Mice and Men",
-    body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
-            bank and runs deep and green. The water is warm too, for it has slipped twinkling \
-            over the yellow sands in the sunlight before reaching the narrow pool. On one \
-            side of the river the golden foothill slopes curve up to the strong and rocky \
-            Gabilan Mountains, but on the valley side the water is lined with trees—willows \
-            fresh and green with every spring, carrying in their lower leaf junctures the \
-            debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
-            limbs and branches that arch over the pool"
-    ));
+    // ### Create a document directly from json.
+    //
+    // Alternatively, we can use our schema to parse a
+    // document object directly from json.
+    // The document is a string, but we use the `json` macro
+    // from `serde_json` for the convenience of multi-line support.
+    let json = json!({
+       "title": "Of Mice and Men",
+       "body": "A few miles south of Soledad, the Salinas River drops in close to the hillside \
+                bank and runs deep and green. The water is warm too, for it has slipped twinkling \
+                over the yellow sands in the sunlight before reaching the narrow pool. On one \
+                side of the river the golden foothill slopes curve up to the strong and rocky \
+                Gabilan Mountains, but on the valley side the water is lined with trees—willows \
+                fresh and green with every spring, carrying in their lower leaf junctures the \
+                debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
+                limbs and branches that arch over the pool"
+    });
+    let mice_and_men_doc = schema.parse_document(&json.to_string())?;
 
-    // Multivalued field just need to be repeated.
-    index_writer.add_document(doc!(
-    title => "Frankenstein",
-    title => "The Modern Prometheus",
-    body => "You will rejoice to hear that no disaster has accompanied the commencement of an \
-             enterprise which you have regarded with such evil forebodings.  I arrived here \
-             yesterday, and my first task is to assure my dear sister of my welfare and \
-             increasing confidence in the success of my undertaking."
-    ));
+    index_writer.add_document(mice_and_men_doc);
+
+    // Multi-valued field are allowed, they are
+    // expressed in JSON by an array.
+    // The following document has two titles.
+    let json = json!({
+       "title": ["Frankenstein", "The Modern Prometheus"],
+       "body": "You will rejoice to hear that no disaster has accompanied the commencement of an \
+                enterprise which you have regarded with such evil forebodings.  I arrived here \
+                yesterday, and my first task is to assure my dear sister of my welfare and \
+                increasing confidence in the success of my undertaking."
+    });
+    let frankenstein_doc = schema.parse_document(&json.to_string())?;
+
+    index_writer.add_document(frankenstein_doc);
 
     // This is an example, so we will only index 3 documents
     // here. You can check out tantivy's tutorial to index
     // the English wikipedia. Tantivy's indexing is rather fast.
     // Indexing 5 million articles of the English wikipedia takes
-    // around 3 minutes on my computer!
+    // around 4 minutes on my computer!
 
     // ### Committing
     //
     // At this point our documents are not searchable.
     //
     //
-    // We need to call `.commit()` explicitly to force the
-    // `index_writer` to finish processing the documents in the queue,
+    // We need to call .commit() explicitly to force the
+    // index_writer to finish processing the documents in the queue,
     // flush the current index to the disk, and advertise
     // the existence of new documents.
     //
@@ -146,42 +155,21 @@ fn main() -> tantivy::Result<()> {
     // persistently indexed.
     //
     // In the scenario of a crash or a power failure,
-    // tantivy behaves as if it has rolled back to its last
+    // tantivy behaves as if has rolled back to its last
     // commit.
 
     // # Searching
     //
-    // ### Searcher
-    //
-    // A reader is required first in order to search an index.
-    // It acts as a `Searcher` pool that reloads itself,
-    // depending on a `ReloadPolicy`.
-    //
-    // For a search server you will typically create one reader for the entire lifetime of your
-    // program, and acquire a new searcher for every single request.
-    //
-    // In the code below, we rely on the 'ON_COMMIT' policy: the reader
-    // will reload the index automatically after each commit.
-    let reader = index
-        .reader_builder()
-        .reload_policy(ReloadPolicy::OnCommit)
-        .try_into()?;
+    // Let's search our index. Start by reloading
+    // searchers in the index. This should be done
+    // after every commit().
+    index.load_searchers()?;
 
-    // We now need to acquire a searcher.
+    // Afterwards create one (or more) searchers.
     //
-    // A searcher points to a snapshotted, immutable version of the index.
-    //
-    // Some search experience might require more than
-    // one query. Using the same searcher ensures that all of these queries will run on the
-    // same version of the index.
-    //
-    // Acquiring a `searcher` is very cheap.
-    //
-    // You should acquire a searcher every time you start processing a request and
-    // and release it right after your query is finished.
-    let searcher = reader.searcher();
-
-    // ### Query
+    // You should create a searcher
+    // every time you start a "search query".
+    let searcher = index.searcher();
 
     // The query parser can interpret human queries.
     // Here, if the user does not specify which
@@ -189,7 +177,7 @@ fn main() -> tantivy::Result<()> {
     // in both title and body.
     let query_parser = QueryParser::for_index(&index, vec![title, body]);
 
-    // `QueryParser` may fail if the query is not in the right
+    // QueryParser may fail if the query is not in the right
     // format. For user facing applications, this can be a problem.
     // A ticket has been opened regarding this problem.
     let query = query_parser.parse_query("sea whale")?;
@@ -205,10 +193,15 @@ fn main() -> tantivy::Result<()> {
     //
     // We are not interested in all of the documents but
     // only in the top 10. Keeping track of our top 10 best documents
-    // is the role of the `TopDocs` collector.
+    // is the role of the TopCollector.
+    let mut top_collector = TopCollector::with_limit(10);
 
     // We can now perform our query.
-    let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
+    searcher.search(&*query, &mut top_collector)?;
+
+    // Our top collector now contains the 10
+    // most relevant doc ids...
+    let doc_addresses = top_collector.docs();
 
     // The actual documents still need to be
     // retrieved from Tantivy's store.
@@ -216,10 +209,17 @@ fn main() -> tantivy::Result<()> {
     // Since the body field was not configured as stored,
     // the document returned will only contain
     // a title.
-    for (_score, doc_address) in top_docs {
-        let retrieved_doc = searcher.doc(doc_address)?;
+
+    for doc_address in doc_addresses {
+        let retrieved_doc = searcher.doc(&doc_address)?;
         println!("{}", schema.to_json(&retrieved_doc));
     }
 
+    // Wait for indexing and merging threads to shut down.
+    // Usually this isn't needed, but in `main` we try to
+    // delete the temporary directory and that fails on
+    // Windows if the files are still open.
+    index_writer.wait_merging_threads()?;
+
     Ok(())
 }

examples/snippet.rs

@@ -1,82 +0,0 @@
-// # Snippet example
-//
-// This example shows how to return a representative snippet of
-// your hit result.
-// Snippet are an extracted of a target document, and returned in HTML format.
-// The keyword searched by the user are highlighted with a `<b>` tag.
-
-// ---
-// Importing tantivy...
-use tantivy::collector::TopDocs;
-use tantivy::query::QueryParser;
-use tantivy::schema::*;
-use tantivy::{doc, Index, Snippet, SnippetGenerator};
-use tempfile::TempDir;
-
-fn main() -> tantivy::Result<()> {
-    // Let's create a temporary directory for the
-    // sake of this example
-    let index_path = TempDir::new()?;
-
-    // # Defining the schema
-    let mut schema_builder = Schema::builder();
-    let title = schema_builder.add_text_field("title", TEXT | STORED);
-    let body = schema_builder.add_text_field("body", TEXT | STORED);
-    let schema = schema_builder.build();
-
-    // # Indexing documents
-    let index = Index::create_in_dir(&index_path, schema)?;
-
-    let mut index_writer = index.writer(50_000_000)?;
-
-    // we'll only need one doc for this example.
-    index_writer.add_document(doc!(
-    title => "Of Mice and Men",
-    body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
-            bank and runs deep and green. The water is warm too, for it has slipped twinkling \
-            over the yellow sands in the sunlight before reaching the narrow pool. On one \
-            side of the river the golden foothill slopes curve up to the strong and rocky \
-            Gabilan Mountains, but on the valley side the water is lined with trees—willows \
-            fresh and green with every spring, carrying in their lower leaf junctures the \
-            debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
-            limbs and branches that arch over the pool"
-    ));
-    // ...
-    index_writer.commit()?;
-
-    let reader = index.reader()?;
-    let searcher = reader.searcher();
-    let query_parser = QueryParser::for_index(&index, vec![title, body]);
-    let query = query_parser.parse_query("sycamore spring")?;
-
-    let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
-
-    let snippet_generator = SnippetGenerator::create(&searcher, &*query, body)?;
-
-    for (score, doc_address) in top_docs {
-        let doc = searcher.doc(doc_address)?;
-        let snippet = snippet_generator.snippet_from_doc(&doc);
-        println!("Document score {}:", score);
-        println!("title: {}", doc.get_first(title).unwrap().text().unwrap());
-        println!("snippet: {}", snippet.to_html());
-        println!("custom highlighting: {}", highlight(snippet));
-    }
-
-    Ok(())
-}
-
-fn highlight(snippet: Snippet) -> String {
-    let mut result = String::new();
-    let mut start_from = 0;
-
-    for fragment_range in snippet.highlighted() {
-        result.push_str(&snippet.fragments()[start_from..fragment_range.start]);
-        result.push_str(" --> ");
-        result.push_str(&snippet.fragments()[fragment_range.clone()]);
-        result.push_str(" <-- ");
-        start_from = fragment_range.end;
-    }
-
-    result.push_str(&snippet.fragments()[start_from..]);
-    result
-}

examples/stop_words.rs

@@ -1,113 +0,0 @@
-// # Stop Words Example
-//
-// This example covers the basic usage of stop words
-// with tantivy
-//
-// We will :
-// - define our schema
-// - create an index in a directory
-// - add a few stop words
-// - index few documents in our index
-
-// ---
-// Importing tantivy...
-use tantivy::collector::TopDocs;
-use tantivy::query::QueryParser;
-use tantivy::schema::*;
-use tantivy::tokenizer::*;
-use tantivy::{doc, Index};
-
-fn main() -> tantivy::Result<()> {
-    // this example assumes you understand the content in `basic_search`
-    let mut schema_builder = Schema::builder();
-
-    // This configures your custom options for how tantivy will
-    // store and process your content in the index; The key
-    // to note is that we are setting the tokenizer to `stoppy`
-    // which will be defined and registered below.
-    let text_field_indexing = TextFieldIndexing::default()
-        .set_tokenizer("stoppy")
-        .set_index_option(IndexRecordOption::WithFreqsAndPositions);
-    let text_options = TextOptions::default()
-        .set_indexing_options(text_field_indexing)
-        .set_stored();
-
-    // Our first field is title.
-    schema_builder.add_text_field("title", text_options);
-
-    // Our second field is body.
-    let text_field_indexing = TextFieldIndexing::default()
-        .set_tokenizer("stoppy")
-        .set_index_option(IndexRecordOption::WithFreqsAndPositions);
-    let text_options = TextOptions::default()
-        .set_indexing_options(text_field_indexing)
-        .set_stored();
-    schema_builder.add_text_field("body", text_options);
-
-    let schema = schema_builder.build();
-
-    let index = Index::create_in_ram(schema.clone());
-
-    // This tokenizer lowers all of the text (to help with stop word matching)
-    // then removes all instances of `the` and `and` from the corpus
-    let tokenizer = TextAnalyzer::from(SimpleTokenizer)
-        .filter(LowerCaser)
-        .filter(StopWordFilter::remove(vec![
-            "the".to_string(),
-            "and".to_string(),
-        ]));
-
-    index.tokenizers().register("stoppy", tokenizer);
-
-    let mut index_writer = index.writer(50_000_000)?;
-
-    let title = schema.get_field("title").unwrap();
-    let body = schema.get_field("body").unwrap();
-
-    index_writer.add_document(doc!(
-    title => "The Old Man and the Sea",
-    body => "He was an old man who fished alone in a skiff in the Gulf Stream and \
-     he had gone eighty-four days now without taking a fish."
-    ));
-
-    index_writer.add_document(doc!(
-    title => "Of Mice and Men",
-    body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
-            bank and runs deep and green. The water is warm too, for it has slipped twinkling \
-            over the yellow sands in the sunlight before reaching the narrow pool. On one \
-            side of the river the golden foothill slopes curve up to the strong and rocky \
-            Gabilan Mountains, but on the valley side the water is lined with trees—willows \
-            fresh and green with every spring, carrying in their lower leaf junctures the \
-            debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
-            limbs and branches that arch over the pool"
-    ));
-
-    index_writer.add_document(doc!(
-    title => "Frankenstein",
-    body => "You will rejoice to hear that no disaster has accompanied the commencement of an \
-             enterprise which you have regarded with such evil forebodings.  I arrived here \
-             yesterday, and my first task is to assure my dear sister of my welfare and \
-             increasing confidence in the success of my undertaking."
-    ));
-
-    index_writer.commit()?;
-
-    let reader = index.reader()?;
-
-    let searcher = reader.searcher();
-
-    let query_parser = QueryParser::for_index(&index, vec![title, body]);
-
-    // stop words are applied on the query as well.
-    // The following will be equivalent to `title:frankenstein`
-    let query = query_parser.parse_query("title:\"the Frankenstein\"")?;
-    let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
-
-    for (score, doc_address) in top_docs {
-        let retrieved_doc = searcher.doc(doc_address)?;
-        println!("\n==\nDocument score {}:", score);
-        println!("{}", schema.to_json(&retrieved_doc));
-    }
-
-    Ok(())
-}

examples/working_with_json.rs

@@ -1,40 +0,0 @@
-use tantivy::schema::*;
-
-// # Document from json
-//
-// For convenience, `Document` can be parsed directly from json.
-fn main() -> tantivy::Result<()> {
-    // Let's first define a schema and an index.
-    // Check out the basic example if this is confusing to you.
-    //
-    // first we need to define a schema ...
-    let mut schema_builder = Schema::builder();
-    schema_builder.add_text_field("title", TEXT | STORED);
-    schema_builder.add_text_field("body", TEXT);
-    schema_builder.add_u64_field("year", INDEXED);
-    let schema = schema_builder.build();
-
-    // Let's assume we have a json-serialized document.
-    let mice_and_men_doc_json = r#"{
-       "title": "Of Mice and Men",
-       "year": 1937
-    }"#;
-
-    // We can parse our document
-    let _mice_and_men_doc = schema.parse_document(mice_and_men_doc_json)?;
-
-    // Multi-valued field are allowed, they are
-    // expressed in JSON by an array.
-    // The following document has two titles.
-    let frankenstein_json = r#"{
-       "title": ["Frankenstein", "The Modern Prometheus"],
-       "year": 1818
-    }"#;
-    let _frankenstein_doc = schema.parse_document(frankenstein_json)?;
-
-    // Note that the schema is saved in your index directory.
-    //
-    // As a result, Indexes are aware of their schema, and you can use this feature
-    // just by opening an existing `Index`, and calling `index.schema()..parse_document(json)`.
-    Ok(())
-}

fastfield_codecs/Cargo.toml

@@ -1,24 +0,0 @@
-[package]
-name = "fastfield_codecs"
-version = "0.1.0"
-authors = ["Pascal Seitz <pascal@quickwit.io>"]
-license = "MIT"
-edition = "2018"
-description = "Fast field codecs used by tantivy"
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-common = { path = "../common/" }
-tantivy-bitpacker = { path = "../bitpacker/" }
-prettytable-rs = {version="0.8.0", optional= true}
-rand = {version="0.8.3", optional= true}
-
-[dev-dependencies]
-more-asserts = "0.2.1"
-rand = "0.8.3"
-
-[features]
-bin = ["prettytable-rs", "rand"]
-default = ["bin"]
-

fastfield_codecs/README.md

@@ -1,68 +0,0 @@
-
-
-# Fast Field Codecs
-
-This crate contains various fast field codecs, used to compress/decompress fast field data in tantivy.
-
-## Contributing
-
-Contributing is pretty straightforward. Since the bitpacking is the simplest compressor, you can check it for reference.
-
-A codec needs to implement 2 traits:
-
-- A reader implementing `FastFieldCodecReader` to read the codec.
-- A serializer implementing `FastFieldCodecSerializer` for compression estimation and codec name + id.
-
-### Tests
-
-Once the traits are implemented test and benchmark integration is pretty easy (see `test_with_codec_data_sets` and `bench.rs`).
-
-Make sure to add the codec to the main.rs, which tests the compression ratio and estimation against different data sets. You can run it with:
-```
-cargo run --features bin
-```
-
-### TODO
-- Add real world data sets in comparison
-- Add codec to cover sparse data sets
-
-
-### Codec Comparison
-```
-+----------------------------------+-------------------+------------------------+
-|                                  | Compression Ratio | Compression Estimation |
-+----------------------------------+-------------------+------------------------+
-| Autoincrement                    |                   |                        |
-+----------------------------------+-------------------+------------------------+
-| LinearInterpol                   | 0.000039572664    | 0.000004396963         |
-+----------------------------------+-------------------+------------------------+
-| MultiLinearInterpol              | 0.1477348         | 0.17275847             |
-+----------------------------------+-------------------+------------------------+
-| Bitpacked                        | 0.28126493        | 0.28125                |
-+----------------------------------+-------------------+------------------------+
-| Monotonically increasing concave |                   |                        |
-+----------------------------------+-------------------+------------------------+
-| LinearInterpol                   | 0.25003937        | 0.26562938             |
-+----------------------------------+-------------------+------------------------+
-| MultiLinearInterpol              | 0.190665          | 0.1883836              |
-+----------------------------------+-------------------+------------------------+
-| Bitpacked                        | 0.31251436        | 0.3125                 |
-+----------------------------------+-------------------+------------------------+
-| Monotonically increasing convex  |                   |                        |
-+----------------------------------+-------------------+------------------------+
-| LinearInterpol                   | 0.25003937        | 0.28125438             |
-+----------------------------------+-------------------+------------------------+
-| MultiLinearInterpol              | 0.18676           | 0.2040086              |
-+----------------------------------+-------------------+------------------------+
-| Bitpacked                        | 0.31251436        | 0.3125                 |
-+----------------------------------+-------------------+------------------------+
-| Almost monotonically increasing  |                   |                        |
-+----------------------------------+-------------------+------------------------+
-| LinearInterpol                   | 0.14066513        | 0.1562544              |
-+----------------------------------+-------------------+------------------------+
-| MultiLinearInterpol              | 0.16335973        | 0.17275847             |
-+----------------------------------+-------------------+------------------------+
-| Bitpacked                        | 0.28126493        | 0.28125                |
-+----------------------------------+-------------------+------------------------+
-
-```

fastfield_codecs/benches/bench.rs

@@ -1,108 +0,0 @@
-#![feature(test)]
-
-extern crate test;
-
-#[cfg(test)]
-mod tests {
-    use fastfield_codecs::{
-        bitpacked::{BitpackedFastFieldReader, BitpackedFastFieldSerializer},
-        linearinterpol::{LinearInterpolFastFieldReader, LinearInterpolFastFieldSerializer},
-        multilinearinterpol::{
-            MultiLinearInterpolFastFieldReader, MultiLinearInterpolFastFieldSerializer,
-        },
-        *,
-    };
-
-    fn get_data() -> Vec<u64> {
-        let mut data: Vec<_> = (100..55000_u64)
-            .map(|num| num + rand::random::<u8>() as u64)
-            .collect();
-        data.push(99_000);
-        data.insert(1000, 2000);
-        data.insert(2000, 100);
-        data.insert(3000, 4100);
-        data.insert(4000, 100);
-        data.insert(5000, 800);
-        data
-    }
-
-    fn value_iter() -> impl Iterator<Item = u64> {
-        0..20_000
-    }
-    fn bench_get<S: FastFieldCodecSerializer, R: FastFieldCodecReader>(
-        b: &mut Bencher,
-        data: &[u64],
-    ) {
-        let mut bytes = vec![];
-        S::serialize(
-            &mut bytes,
-            &data,
-            stats_from_vec(data),
-            data.iter().cloned(),
-            data.iter().cloned(),
-        )
-        .unwrap();
-        let reader = R::open_from_bytes(&bytes).unwrap();
-        b.iter(|| {
-            for pos in value_iter() {
-                reader.get_u64(pos as u64, &bytes);
-            }
-        });
-    }
-    fn bench_create<S: FastFieldCodecSerializer>(b: &mut Bencher, data: &[u64]) {
-        let mut bytes = vec![];
-        b.iter(|| {
-            S::serialize(
-                &mut bytes,
-                &data,
-                stats_from_vec(data),
-                data.iter().cloned(),
-                data.iter().cloned(),
-            )
-            .unwrap();
-        });
-    }
-
-    use test::Bencher;
-    #[bench]
-    fn bench_fastfield_bitpack_create(b: &mut Bencher) {
-        let data: Vec<_> = get_data();
-        bench_create::<BitpackedFastFieldSerializer>(b, &data);
-    }
-    #[bench]
-    fn bench_fastfield_linearinterpol_create(b: &mut Bencher) {
-        let data: Vec<_> = get_data();
-        bench_create::<LinearInterpolFastFieldSerializer>(b, &data);
-    }
-    #[bench]
-    fn bench_fastfield_multilinearinterpol_create(b: &mut Bencher) {
-        let data: Vec<_> = get_data();
-        bench_create::<MultiLinearInterpolFastFieldSerializer>(b, &data);
-    }
-    #[bench]
-    fn bench_fastfield_bitpack_get(b: &mut Bencher) {
-        let data: Vec<_> = get_data();
-        bench_get::<BitpackedFastFieldSerializer, BitpackedFastFieldReader>(b, &data);
-    }
-    #[bench]
-    fn bench_fastfield_linearinterpol_get(b: &mut Bencher) {
-        let data: Vec<_> = get_data();
-        bench_get::<LinearInterpolFastFieldSerializer, LinearInterpolFastFieldReader>(b, &data);
-    }
-    #[bench]
-    fn bench_fastfield_multilinearinterpol_get(b: &mut Bencher) {
-        let data: Vec<_> = get_data();
-        bench_get::<MultiLinearInterpolFastFieldSerializer, MultiLinearInterpolFastFieldReader>(
-            b, &data,
-        );
-    }
-    pub fn stats_from_vec(data: &[u64]) -> FastFieldStats {
-        let min_value = data.iter().cloned().min().unwrap_or(0);
-        let max_value = data.iter().cloned().max().unwrap_or(0);
-        FastFieldStats {
-            min_value,
-            max_value,
-            num_vals: data.len() as u64,
-        }
-    }
-}

fastfield_codecs/src/bitpacked.rs

@@ -1,176 +0,0 @@
-use crate::FastFieldCodecReader;
-use crate::FastFieldCodecSerializer;
-use crate::FastFieldDataAccess;
-use crate::FastFieldStats;
-use common::BinarySerializable;
-use std::io::{self, Write};
-use tantivy_bitpacker::compute_num_bits;
-use tantivy_bitpacker::BitPacker;
-
-use tantivy_bitpacker::BitUnpacker;
-
-/// Depending on the field type, a different
-/// fast field is required.
-#[derive(Clone)]
-pub struct BitpackedFastFieldReader {
-    bit_unpacker: BitUnpacker,
-    pub min_value_u64: u64,
-    pub max_value_u64: u64,
-}
-
-impl<'data> FastFieldCodecReader for BitpackedFastFieldReader {
-    /// Opens a fast field given a file.
-    fn open_from_bytes(bytes: &[u8]) -> io::Result<Self> {
-        let (_data, mut footer) = bytes.split_at(bytes.len() - 16);
-        let min_value = u64::deserialize(&mut footer)?;
-        let amplitude = u64::deserialize(&mut footer)?;
-        let max_value = min_value + amplitude;
-        let num_bits = compute_num_bits(amplitude);
-        let bit_unpacker = BitUnpacker::new(num_bits);
-        Ok(BitpackedFastFieldReader {
-            min_value_u64: min_value,
-            max_value_u64: max_value,
-            bit_unpacker,
-        })
-    }
-    #[inline]
-    fn get_u64(&self, doc: u64, data: &[u8]) -> u64 {
-        self.min_value_u64 + self.bit_unpacker.get(doc, data)
-    }
-    #[inline]
-    fn min_value(&self) -> u64 {
-        self.min_value_u64
-    }
-    #[inline]
-    fn max_value(&self) -> u64 {
-        self.max_value_u64
-    }
-}
-pub struct BitpackedFastFieldSerializerLegacy<'a, W: 'a + Write> {
-    bit_packer: BitPacker,
-    write: &'a mut W,
-    min_value: u64,
-    amplitude: u64,
-    num_bits: u8,
-}
-
-impl<'a, W: Write> BitpackedFastFieldSerializerLegacy<'a, W> {
-    /// Creates a new fast field serializer.
-    ///
-    /// The serializer in fact encode the values by bitpacking
-    /// `(val - min_value)`.
-    ///
-    /// It requires a `min_value` and a `max_value` to compute
-    /// compute the minimum number of bits required to encode
-    /// values.
-    pub fn open(
-        write: &'a mut W,
-        min_value: u64,
-        max_value: u64,
-    ) -> io::Result<BitpackedFastFieldSerializerLegacy<'a, W>> {
-        assert!(min_value <= max_value);
-        let amplitude = max_value - min_value;
-        let num_bits = compute_num_bits(amplitude);
-        let bit_packer = BitPacker::new();
-        Ok(BitpackedFastFieldSerializerLegacy {
-            bit_packer,
-            write,
-            min_value,
-            amplitude,
-            num_bits,
-        })
-    }
-    /// Pushes a new value to the currently open u64 fast field.
-    #[inline]
-    pub fn add_val(&mut self, val: u64) -> io::Result<()> {
-        let val_to_write: u64 = val - self.min_value;
-        self.bit_packer
-            .write(val_to_write, self.num_bits, &mut self.write)?;
-        Ok(())
-    }
-    pub fn close_field(mut self) -> io::Result<()> {
-        self.bit_packer.close(&mut self.write)?;
-        self.min_value.serialize(&mut self.write)?;
-        self.amplitude.serialize(&mut self.write)?;
-        Ok(())
-    }
-}
-
-pub struct BitpackedFastFieldSerializer {}
-
-impl FastFieldCodecSerializer for BitpackedFastFieldSerializer {
-    const NAME: &'static str = "Bitpacked";
-    const ID: u8 = 1;
-    /// Serializes data with the BitpackedFastFieldSerializer.
-    ///
-    /// The serializer in fact encode the values by bitpacking
-    /// `(val - min_value)`.
-    ///
-    /// It requires a `min_value` and a `max_value` to compute
-    /// compute the minimum number of bits required to encode
-    /// values.
-    fn serialize(
-        write: &mut impl Write,
-        _fastfield_accessor: &impl FastFieldDataAccess,
-        stats: FastFieldStats,
-        data_iter: impl Iterator<Item = u64>,
-        _data_iter1: impl Iterator<Item = u64>,
-    ) -> io::Result<()> {
-        let mut serializer =
-            BitpackedFastFieldSerializerLegacy::open(write, stats.min_value, stats.max_value)?;
-
-        for val in data_iter {
-            serializer.add_val(val)?;
-        }
-        serializer.close_field()?;
-
-        Ok(())
-    }
-    fn is_applicable(
-        _fastfield_accessor: &impl FastFieldDataAccess,
-        _stats: FastFieldStats,
-    ) -> bool {
-        true
-    }
-    fn estimate(_fastfield_accessor: &impl FastFieldDataAccess, stats: FastFieldStats) -> f32 {
-        let amplitude = stats.max_value - stats.min_value;
-        let num_bits = compute_num_bits(amplitude);
-        let num_bits_uncompressed = 64;
-        num_bits as f32 / num_bits_uncompressed as f32
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use crate::tests::get_codec_test_data_sets;
-
-    fn create_and_validate(data: &[u64], name: &str) {
-        crate::tests::create_and_validate::<BitpackedFastFieldSerializer, BitpackedFastFieldReader>(
-            data, name,
-        );
-    }
-
-    #[test]
-    fn test_with_codec_data_sets() {
-        let data_sets = get_codec_test_data_sets();
-        for (mut data, name) in data_sets {
-            create_and_validate(&data, name);
-            data.reverse();
-            create_and_validate(&data, name);
-        }
-    }
-
-    #[test]
-    fn bitpacked_fast_field_rand() {
-        for _ in 0..500 {
-            let mut data = (0..1 + rand::random::<u8>() as usize)
-                .map(|_| rand::random::<i64>() as u64 / 2)
-                .collect::<Vec<_>>();
-            create_and_validate(&data, "rand");
-
-            data.reverse();
-            create_and_validate(&data, "rand");
-        }
-    }
-}

fastfield_codecs/src/lib.rs

@@ -1,225 +0,0 @@
-#[cfg(test)]
-#[macro_use]
-extern crate more_asserts;
-
-use std::io;
-use std::io::Write;
-
-pub mod bitpacked;
-pub mod linearinterpol;
-pub mod multilinearinterpol;
-
-pub trait FastFieldCodecReader: Sized {
-    /// reads the metadata and returns the CodecReader
-    fn open_from_bytes(bytes: &[u8]) -> std::io::Result<Self>;
-
-    fn get_u64(&self, doc: u64, data: &[u8]) -> u64;
-
-    fn min_value(&self) -> u64;
-    fn max_value(&self) -> u64;
-}
-
-/// The FastFieldSerializerEstimate trait is required on all variants
-/// of fast field compressions, to decide which one to choose.
-pub trait FastFieldCodecSerializer {
-    /// A codex needs to provide a unique name and id, which is
-    /// used for debugging and de/serialization.
-    const NAME: &'static str;
-    const ID: u8;
-
-    /// Check if the Codec is able to compress the data
-    fn is_applicable(fastfield_accessor: &impl FastFieldDataAccess, stats: FastFieldStats) -> bool;
-
-    /// Returns an estimate of the compression ratio.
-    /// The baseline is uncompressed 64bit data.
-    ///
-    /// It could make sense to also return a value representing
-    /// computational complexity.
-    fn estimate(fastfield_accessor: &impl FastFieldDataAccess, stats: FastFieldStats) -> f32;
-
-    /// Serializes the data using the serializer into write.
-    /// There are multiple iterators, in case the codec needs to read the data multiple times.
-    /// The iterators should be preferred over using fastfield_accessor for performance reasons.
-    fn serialize(
-        write: &mut impl Write,
-        fastfield_accessor: &impl FastFieldDataAccess,
-        stats: FastFieldStats,
-        data_iter: impl Iterator<Item = u64>,
-        data_iter1: impl Iterator<Item = u64>,
-    ) -> io::Result<()>;
-}
-
-/// FastFieldDataAccess is the trait to access fast field data during serialization and estimation.
-pub trait FastFieldDataAccess {
-    /// Return the value associated to the given position.
-    ///
-    /// Whenever possible use the Iterator passed to the fastfield creation instead, for performance reasons.
-    ///
-    /// # Panics
-    ///
-    /// May panic if `position` is greater than the index.
-    fn get_val(&self, position: u64) -> u64;
-}
-
-#[derive(Debug, Clone)]
-pub struct FastFieldStats {
-    pub min_value: u64,
-    pub max_value: u64,
-    pub num_vals: u64,
-}
-
-impl<'a> FastFieldDataAccess for &'a [u64] {
-    fn get_val(&self, position: u64) -> u64 {
-        self[position as usize]
-    }
-}
-
-impl FastFieldDataAccess for Vec<u64> {
-    fn get_val(&self, position: u64) -> u64 {
-        self[position as usize]
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use crate::{
-        bitpacked::{BitpackedFastFieldReader, BitpackedFastFieldSerializer},
-        linearinterpol::{LinearInterpolFastFieldReader, LinearInterpolFastFieldSerializer},
-        multilinearinterpol::{
-            MultiLinearInterpolFastFieldReader, MultiLinearInterpolFastFieldSerializer,
-        },
-    };
-
-    pub fn create_and_validate<S: FastFieldCodecSerializer, R: FastFieldCodecReader>(
-        data: &[u64],
-        name: &str,
-    ) -> (f32, f32) {
-        if !S::is_applicable(&data, crate::tests::stats_from_vec(data)) {
-            return (f32::MAX, 0.0);
-        }
-        let estimation = S::estimate(&data, crate::tests::stats_from_vec(data));
-        let mut out = vec![];
-        S::serialize(
-            &mut out,
-            &data,
-            crate::tests::stats_from_vec(data),
-            data.iter().cloned(),
-            data.iter().cloned(),
-        )
-        .unwrap();
-
-        let reader = R::open_from_bytes(&out).unwrap();
-        for (doc, orig_val) in data.iter().enumerate() {
-            let val = reader.get_u64(doc as u64, &out);
-            if val != *orig_val {
-                panic!(
-                    "val {:?} does not match orig_val {:?}, in data set {}, data {:?}",
-                    val, orig_val, name, data
-                );
-            }
-        }
-        let actual_compression = data.len() as f32 / out.len() as f32;
-        (estimation, actual_compression)
-    }
-    pub fn get_codec_test_data_sets() -> Vec<(Vec<u64>, &'static str)> {
-        let mut data_and_names = vec![];
-
-        let data = (10..=20_u64).collect::<Vec<_>>();
-        data_and_names.push((data, "simple monotonically increasing"));
-
-        data_and_names.push((
-            vec![5, 6, 7, 8, 9, 10, 99, 100],
-            "offset in linear interpol",
-        ));
-        data_and_names.push((vec![5, 50, 3, 13, 1, 1000, 35], "rand small"));
-        data_and_names.push((vec![10], "single value"));
-
-        data_and_names
-    }
-
-    fn test_codec<S: FastFieldCodecSerializer, R: FastFieldCodecReader>() {
-        let codec_name = S::NAME;
-        for (data, data_set_name) in get_codec_test_data_sets() {
-            let (estimate, actual) =
-                crate::tests::create_and_validate::<S, R>(&data, data_set_name);
-            let result = if estimate == f32::MAX {
-                "Disabled".to_string()
-            } else {
-                format!("Estimate {:?} Actual {:?} ", estimate, actual)
-            };
-            println!(
-                "Codec {}, DataSet {}, {}",
-                codec_name, data_set_name, result
-            );
-        }
-    }
-    #[test]
-    fn test_codec_bitpacking() {
-        test_codec::<BitpackedFastFieldSerializer, BitpackedFastFieldReader>();
-    }
-    #[test]
-    fn test_codec_interpolation() {
-        test_codec::<LinearInterpolFastFieldSerializer, LinearInterpolFastFieldReader>();
-    }
-    #[test]
-    fn test_codec_multi_interpolation() {
-        test_codec::<MultiLinearInterpolFastFieldSerializer, MultiLinearInterpolFastFieldReader>();
-    }
-
-    use super::*;
-    pub fn stats_from_vec(data: &[u64]) -> FastFieldStats {
-        let min_value = data.iter().cloned().min().unwrap_or(0);
-        let max_value = data.iter().cloned().max().unwrap_or(0);
-        FastFieldStats {
-            min_value,
-            max_value,
-            num_vals: data.len() as u64,
-        }
-    }
-
-    #[test]
-    fn estimation_good_interpolation_case() {
-        let data = (10..=20000_u64).collect::<Vec<_>>();
-
-        let linear_interpol_estimation =
-            LinearInterpolFastFieldSerializer::estimate(&data, stats_from_vec(&data));
-        assert_le!(linear_interpol_estimation, 0.01);
-
-        let multi_linear_interpol_estimation =
-            MultiLinearInterpolFastFieldSerializer::estimate(&data, stats_from_vec(&data));
-        assert_le!(multi_linear_interpol_estimation, 0.2);
-        assert_le!(linear_interpol_estimation, multi_linear_interpol_estimation);
-
-        let bitpacked_estimation =
-            BitpackedFastFieldSerializer::estimate(&data, stats_from_vec(&data));
-        assert_le!(linear_interpol_estimation, bitpacked_estimation);
-    }
-    #[test]
-    fn estimation_test_bad_interpolation_case() {
-        let data = vec![200, 10, 10, 10, 10, 1000, 20];
-
-        let linear_interpol_estimation =
-            LinearInterpolFastFieldSerializer::estimate(&data, stats_from_vec(&data));
-        assert_le!(linear_interpol_estimation, 0.32);
-
-        let bitpacked_estimation =
-            BitpackedFastFieldSerializer::estimate(&data, stats_from_vec(&data));
-        assert_le!(bitpacked_estimation, linear_interpol_estimation);
-    }
-    #[test]
-    fn estimation_test_bad_interpolation_case_monotonically_increasing() {
-        let mut data = (200..=20000_u64).collect::<Vec<_>>();
-        data.push(1_000_000);
-
-        // in this case the linear interpolation can't in fact not be worse than bitpacking,
-        // but the estimator adds some threshold, which leads to estimated worse behavior
-        let linear_interpol_estimation =
-            LinearInterpolFastFieldSerializer::estimate(&data, stats_from_vec(&data));
-        assert_le!(linear_interpol_estimation, 0.35);
-
-        let bitpacked_estimation =
-            BitpackedFastFieldSerializer::estimate(&data, stats_from_vec(&data));
-        assert_le!(bitpacked_estimation, 0.32);
-        assert_le!(bitpacked_estimation, linear_interpol_estimation);
-    }
-}

fastfield_codecs/src/linearinterpol.rs

@@ -1,295 +0,0 @@
-use crate::FastFieldCodecReader;
-use crate::FastFieldCodecSerializer;
-use crate::FastFieldDataAccess;
-use crate::FastFieldStats;
-use std::io::{self, Read, Write};
-use std::ops::Sub;
-use tantivy_bitpacker::compute_num_bits;
-use tantivy_bitpacker::BitPacker;
-
-use common::BinarySerializable;
-use common::FixedSize;
-use tantivy_bitpacker::BitUnpacker;
-
-/// Depending on the field type, a different
-/// fast field is required.
-#[derive(Clone)]
-pub struct LinearInterpolFastFieldReader {
-    bit_unpacker: BitUnpacker,
-    pub footer: LinearInterpolFooter,
-    pub slope: f32,
-}
-
-#[derive(Clone, Debug)]
-pub struct LinearInterpolFooter {
-    pub relative_max_value: u64,
-    pub offset: u64,
-    pub first_val: u64,
-    pub last_val: u64,
-    pub num_vals: u64,
-    pub min_value: u64,
-    pub max_value: u64,
-}
-
-impl BinarySerializable for LinearInterpolFooter {
-    fn serialize<W: Write>(&self, write: &mut W) -> io::Result<()> {
-        self.relative_max_value.serialize(write)?;
-        self.offset.serialize(write)?;
-        self.first_val.serialize(write)?;
-        self.last_val.serialize(write)?;
-        self.num_vals.serialize(write)?;
-        self.min_value.serialize(write)?;
-        self.max_value.serialize(write)?;
-        Ok(())
-    }
-
-    fn deserialize<R: Read>(reader: &mut R) -> io::Result<LinearInterpolFooter> {
-        Ok(LinearInterpolFooter {
-            relative_max_value: u64::deserialize(reader)?,
-            offset: u64::deserialize(reader)?,
-            first_val: u64::deserialize(reader)?,
-            last_val: u64::deserialize(reader)?,
-            num_vals: u64::deserialize(reader)?,
-            min_value: u64::deserialize(reader)?,
-            max_value: u64::deserialize(reader)?,
-        })
-    }
-}
-
-impl FixedSize for LinearInterpolFooter {
-    const SIZE_IN_BYTES: usize = 56;
-}
-
-impl FastFieldCodecReader for LinearInterpolFastFieldReader {
-    /// Opens a fast field given a file.
-    fn open_from_bytes(bytes: &[u8]) -> io::Result<Self> {
-        let (_data, mut footer) = bytes.split_at(bytes.len() - LinearInterpolFooter::SIZE_IN_BYTES);
-        let footer = LinearInterpolFooter::deserialize(&mut footer)?;
-        let slope = get_slope(footer.first_val, footer.last_val, footer.num_vals);
-
-        let num_bits = compute_num_bits(footer.relative_max_value);
-        let bit_unpacker = BitUnpacker::new(num_bits);
-        Ok(LinearInterpolFastFieldReader {
-            bit_unpacker,
-            footer,
-            slope,
-        })
-    }
-    #[inline]
-    fn get_u64(&self, doc: u64, data: &[u8]) -> u64 {
-        let calculated_value = get_calculated_value(self.footer.first_val, doc, self.slope);
-        (calculated_value + self.bit_unpacker.get(doc, data)) - self.footer.offset
-    }
-
-    #[inline]
-    fn min_value(&self) -> u64 {
-        self.footer.min_value
-    }
-    #[inline]
-    fn max_value(&self) -> u64 {
-        self.footer.max_value
-    }
-}
-
-/// Fastfield serializer, which tries to guess values by linear interpolation
-/// and stores the difference bitpacked.
-pub struct LinearInterpolFastFieldSerializer {}
-
-#[inline]
-fn get_slope(first_val: u64, last_val: u64, num_vals: u64) -> f32 {
-    if num_vals <= 1 {
-        return 0.0;
-    }
-    //  We calculate the slope with f64 high precision and use the result in lower precision f32
-    //  This is done in order to handle estimations for very large values like i64::MAX
-    ((last_val as f64 - first_val as f64) / (num_vals as u64 - 1) as f64) as f32
-}
-
-#[inline]
-fn get_calculated_value(first_val: u64, pos: u64, slope: f32) -> u64 {
-    first_val + (pos as f32 * slope) as u64
-}
-
-impl FastFieldCodecSerializer for LinearInterpolFastFieldSerializer {
-    const NAME: &'static str = "LinearInterpol";
-    const ID: u8 = 2;
-    /// Creates a new fast field serializer.
-    fn serialize(
-        write: &mut impl Write,
-        fastfield_accessor: &impl FastFieldDataAccess,
-        stats: FastFieldStats,
-        data_iter: impl Iterator<Item = u64>,
-        data_iter1: impl Iterator<Item = u64>,
-    ) -> io::Result<()> {
-        assert!(stats.min_value <= stats.max_value);
-
-        let first_val = fastfield_accessor.get_val(0);
-        let last_val = fastfield_accessor.get_val(stats.num_vals as u64 - 1);
-        let slope = get_slope(first_val, last_val, stats.num_vals);
-        // calculate offset to ensure all values are positive
-        let mut offset = 0;
-        let mut rel_positive_max = 0;
-        for (pos, actual_value) in data_iter1.enumerate() {
-            let calculated_value = get_calculated_value(first_val, pos as u64, slope);
-            if calculated_value > actual_value {
-                // negative value we need to apply an offset
-                // we ignore negative values in the max value calculation, because negative values
-                // will be offset to 0
-                offset = offset.max(calculated_value - actual_value);
-            } else {
-                //positive value no offset reuqired
-                rel_positive_max = rel_positive_max.max(actual_value - calculated_value);
-            }
-        }
-
-        // rel_positive_max will be adjusted by offset
-        let relative_max_value = rel_positive_max + offset;
-
-        let num_bits = compute_num_bits(relative_max_value);
-        let mut bit_packer = BitPacker::new();
-        for (pos, val) in data_iter.enumerate() {
-            let calculated_value = get_calculated_value(first_val, pos as u64, slope);
-            let diff = (val + offset) - calculated_value;
-            bit_packer.write(diff, num_bits, write)?;
-        }
-        bit_packer.close(write)?;
-
-        let footer = LinearInterpolFooter {
-            relative_max_value,
-            offset,
-            first_val,
-            last_val,
-            num_vals: stats.num_vals,
-            min_value: stats.min_value,
-            max_value: stats.max_value,
-        };
-        footer.serialize(write)?;
-        Ok(())
-    }
-    fn is_applicable(
-        _fastfield_accessor: &impl FastFieldDataAccess,
-        stats: FastFieldStats,
-    ) -> bool {
-        if stats.num_vals < 3 {
-            return false; //disable compressor for this case
-        }
-        // On serialisation the offset is added to the actual value.
-        // We need to make sure this won't run into overflow calculation issues.
-        // For this we take the maximum theroretical offset and add this to the max value.
-        // If this doesn't overflow the algortihm should be fine
-        let theorethical_maximum_offset = stats.max_value - stats.min_value;
-        if stats
-            .max_value
-            .checked_add(theorethical_maximum_offset)
-            .is_none()
-        {
-            return false;
-        }
-        true
-    }
-    /// estimation for linear interpolation is hard because, you don't know
-    /// where the local maxima for the deviation of the calculated value are and
-    /// the offset to shift all values to >=0 is also unknown.
-    fn estimate(fastfield_accessor: &impl FastFieldDataAccess, stats: FastFieldStats) -> f32 {
-        let first_val = fastfield_accessor.get_val(0);
-        let last_val = fastfield_accessor.get_val(stats.num_vals as u64 - 1);
-        let slope = get_slope(first_val, last_val, stats.num_vals);
-
-        // let's sample at 0%, 5%, 10% .. 95%, 100%
-        let num_vals = stats.num_vals as f32 / 100.0;
-        let sample_positions = (0..20)
-            .map(|pos| (num_vals * pos as f32 * 5.0) as usize)
-            .collect::<Vec<_>>();
-
-        let max_distance = sample_positions
-            .iter()
-            .map(|pos| {
-                let calculated_value = get_calculated_value(first_val, *pos as u64, slope);
-                let actual_value = fastfield_accessor.get_val(*pos as u64);
-                distance(calculated_value, actual_value)
-            })
-            .max()
-            .unwrap_or(0);
-
-        // the theory would be that we don't have the actual max_distance, but we are close within 50%
-        // threshold.
-        // It is multiplied by 2 because in a log case scenario the line would be as much above as
-        // below. So the offset would = max_distance
-        //
-        let relative_max_value = (max_distance as f32 * 1.5) * 2.0;
-
-        let num_bits = compute_num_bits(relative_max_value as u64) as u64 * stats.num_vals as u64
-            + LinearInterpolFooter::SIZE_IN_BYTES as u64;
-        let num_bits_uncompressed = 64 * stats.num_vals;
-        num_bits as f32 / num_bits_uncompressed as f32
-    }
-}
-
-#[inline]
-fn distance<T: Sub<Output = T> + Ord>(x: T, y: T) -> T {
-    if x < y {
-        y - x
-    } else {
-        x - y
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use crate::tests::get_codec_test_data_sets;
-
-    fn create_and_validate(data: &[u64], name: &str) {
-        crate::tests::create_and_validate::<
-            LinearInterpolFastFieldSerializer,
-            LinearInterpolFastFieldReader,
-        >(data, name);
-    }
-
-    #[test]
-    fn test_with_codec_data_sets() {
-        let data_sets = get_codec_test_data_sets();
-        for (mut data, name) in data_sets {
-            create_and_validate(&data, name);
-            data.reverse();
-            create_and_validate(&data, name);
-        }
-    }
-    #[test]
-    fn linear_interpol_fast_field_test_large_amplitude() {
-        let data = vec![
-            i64::MAX as u64 / 2,
-            i64::MAX as u64 / 3,
-            i64::MAX as u64 / 2,
-        ];
-
-        create_and_validate(&data, "large amplitude");
-    }
-    #[test]
-    fn linear_interpol_fast_concave_data() {
-        let data = vec![0, 1, 2, 5, 8, 10, 20, 50];
-        create_and_validate(&data, "concave data");
-    }
-    #[test]
-    fn linear_interpol_fast_convex_data() {
-        let data = vec![0, 40, 60, 70, 75, 77];
-        create_and_validate(&data, "convex data");
-    }
-    #[test]
-    fn linear_interpol_fast_field_test_simple() {
-        let data = (10..=20_u64).collect::<Vec<_>>();
-
-        create_and_validate(&data, "simple monotonically");
-    }
-
-    #[test]
-    fn linear_interpol_fast_field_rand() {
-        for _ in 0..5000 {
-            let mut data = (0..50).map(|_| rand::random::<u64>()).collect::<Vec<_>>();
-            create_and_validate(&data, "random");
-
-            data.reverse();
-            create_and_validate(&data, "random");
-        }
-    }
-}

fastfield_codecs/src/main.rs

@@ -1,127 +0,0 @@
-#[macro_use]
-extern crate prettytable;
-use fastfield_codecs::{
-    linearinterpol::LinearInterpolFastFieldSerializer,
-    multilinearinterpol::MultiLinearInterpolFastFieldSerializer, FastFieldCodecSerializer,
-    FastFieldStats,
-};
-use prettytable::{Cell, Row, Table};
-
-fn main() {
-    let mut table = Table::new();
-
-    // Add a row per time
-    table.add_row(row!["", "Compression Ratio", "Compression Estimation"]);
-
-    for (data, data_set_name) in get_codec_test_data_sets() {
-        let mut results = vec![];
-        let res = serialize_with_codec::<LinearInterpolFastFieldSerializer>(&data);
-        results.push(res);
-        let res = serialize_with_codec::<MultiLinearInterpolFastFieldSerializer>(&data);
-        results.push(res);
-        let res = serialize_with_codec::<fastfield_codecs::bitpacked::BitpackedFastFieldSerializer>(
-            &data,
-        );
-        results.push(res);
-
-        //let best_estimation_codec = results
-        //.iter()
-        //.min_by(|res1, res2| res1.partial_cmp(&res2).unwrap())
-        //.unwrap();
-        let best_compression_ratio_codec = results
-            .iter()
-            .min_by(|res1, res2| res1.partial_cmp(res2).unwrap())
-            .cloned()
-            .unwrap();
-
-        table.add_row(Row::new(vec![Cell::new(data_set_name).style_spec("Bbb")]));
-        for (is_applicable, est, comp, name) in results {
-            let (est_cell, ratio_cell) = if !is_applicable {
-                ("Codec Disabled".to_string(), "".to_string())
-            } else {
-                (est.to_string(), comp.to_string())
-            };
-            #[allow(clippy::all)]
-            let style = if comp == best_compression_ratio_codec.1 {
-                "Fb"
-            } else {
-                ""
-            };
-
-            table.add_row(Row::new(vec![
-                Cell::new(&name.to_string()).style_spec("bFg"),
-                Cell::new(&ratio_cell).style_spec(style),
-                Cell::new(&est_cell).style_spec(""),
-            ]));
-        }
-    }
-
-    table.printstd();
-}
-
-pub fn get_codec_test_data_sets() -> Vec<(Vec<u64>, &'static str)> {
-    let mut data_and_names = vec![];
-
-    let data = (1000..=200_000_u64).collect::<Vec<_>>();
-    data_and_names.push((data, "Autoincrement"));
-
-    let mut current_cumulative = 0;
-    let data = (1..=200_000_u64)
-        .map(|num| {
-            let num = (num as f32 + num as f32).log10() as u64;
-            current_cumulative += num;
-            current_cumulative
-        })
-        .collect::<Vec<_>>();
-    //let data = (1..=200000_u64).map(|num| num + num).collect::<Vec<_>>();
-    data_and_names.push((data, "Monotonically increasing concave"));
-
-    let mut current_cumulative = 0;
-    let data = (1..=200_000_u64)
-        .map(|num| {
-            let num = (200_000.0 - num as f32).log10() as u64;
-            current_cumulative += num;
-            current_cumulative
-        })
-        .collect::<Vec<_>>();
-    data_and_names.push((data, "Monotonically increasing convex"));
-
-    let data = (1000..=200_000_u64)
-        .map(|num| num + rand::random::<u8>() as u64)
-        .collect::<Vec<_>>();
-    data_and_names.push((data, "Almost monotonically increasing"));
-
-    data_and_names
-}
-
-pub fn serialize_with_codec<S: FastFieldCodecSerializer>(
-    data: &[u64],
-) -> (bool, f32, f32, &'static str) {
-    let is_applicable = S::is_applicable(&data, stats_from_vec(data));
-    if !is_applicable {
-        return (false, 0.0, 0.0, S::NAME);
-    }
-    let estimation = S::estimate(&data, stats_from_vec(data));
-    let mut out = vec![];
-    S::serialize(
-        &mut out,
-        &data,
-        stats_from_vec(data),
-        data.iter().cloned(),
-        data.iter().cloned(),
-    )
-    .unwrap();
-
-    let actual_compression = out.len() as f32 / (data.len() * 8) as f32;
-    (true, estimation, actual_compression, S::NAME)
-}
-
-pub fn stats_from_vec(data: &[u64]) -> FastFieldStats {
-    let min_value = data.iter().cloned().min().unwrap_or(0);
-    let max_value = data.iter().cloned().max().unwrap_or(0);
-    FastFieldStats {
-        min_value,
-        max_value,
-        num_vals: data.len() as u64,
-    }
-}

fastfield_codecs/src/multilinearinterpol.rs

@@ -1,411 +0,0 @@
-use crate::FastFieldCodecReader;
-use crate::FastFieldCodecSerializer;
-use crate::FastFieldDataAccess;
-use crate::FastFieldStats;
-use common::CountingWriter;
-use std::io::{self, Read, Write};
-use std::ops::Sub;
-use tantivy_bitpacker::compute_num_bits;
-use tantivy_bitpacker::BitPacker;
-
-use common::BinarySerializable;
-use common::DeserializeFrom;
-use tantivy_bitpacker::BitUnpacker;
-
-const CHUNK_SIZE: u64 = 512;
-
-/// Depending on the field type, a different
-/// fast field is required.
-#[derive(Clone)]
-pub struct MultiLinearInterpolFastFieldReader {
-    pub footer: MultiLinearInterpolFooter,
-}
-
-#[derive(Clone, Debug, Default)]
-struct Function {
-    // The offset in the data is required, because we have diffrent bit_widths per block
-    data_start_offset: u64,
-    // start_pos in the block will be CHUNK_SIZE * BLOCK_NUM
-    start_pos: u64,
-    // only used during serialization, 0 after deserialization
-    end_pos: u64,
-    // only used during serialization, 0 after deserialization
-    value_start_pos: u64,
-    // only used during serialization, 0 after deserialization
-    value_end_pos: u64,
-    slope: f32,
-    // The offset so that all values are positive when writing them
-    positive_val_offset: u64,
-    num_bits: u8,
-    bit_unpacker: BitUnpacker,
-}
-
-impl Function {
-    fn calc_slope(&mut self) {
-        let num_vals = self.end_pos - self.start_pos;
-        get_slope(self.value_start_pos, self.value_end_pos, num_vals);
-    }
-    // split the interpolation into two function, change self and return the second split
-    fn split(&mut self, split_pos: u64, split_pos_value: u64) -> Function {
-        let mut new_function = Function {
-            start_pos: split_pos,
-            end_pos: self.end_pos,
-            value_start_pos: split_pos_value,
-            value_end_pos: self.value_end_pos,
-            ..Default::default()
-        };
-        new_function.calc_slope();
-        self.end_pos = split_pos;
-        self.value_end_pos = split_pos_value;
-        self.calc_slope();
-        new_function
-    }
-}
-
-impl BinarySerializable for Function {
-    fn serialize<W: Write>(&self, write: &mut W) -> io::Result<()> {
-        self.data_start_offset.serialize(write)?;
-        self.value_start_pos.serialize(write)?;
-        self.positive_val_offset.serialize(write)?;
-        self.slope.serialize(write)?;
-        self.num_bits.serialize(write)?;
-        Ok(())
-    }
-
-    fn deserialize<R: Read>(reader: &mut R) -> io::Result<Function> {
-        let data_start_offset = u64::deserialize(reader)?;
-        let value_start_pos = u64::deserialize(reader)?;
-        let offset = u64::deserialize(reader)?;
-        let slope = f32::deserialize(reader)?;
-        let num_bits = u8::deserialize(reader)?;
-        let interpolation = Function {
-            data_start_offset,
-            value_start_pos,
-            positive_val_offset: offset,
-            num_bits,
-            bit_unpacker: BitUnpacker::new(num_bits),
-            slope,
-            ..Default::default()
-        };
-
-        Ok(interpolation)
-    }
-}
-
-#[derive(Clone, Debug)]
-pub struct MultiLinearInterpolFooter {
-    pub num_vals: u64,
-    pub min_value: u64,
-    pub max_value: u64,
-    interpolations: Vec<Function>,
-}
-
-impl BinarySerializable for MultiLinearInterpolFooter {
-    fn serialize<W: Write>(&self, write: &mut W) -> io::Result<()> {
-        let mut out = vec![];
-        self.num_vals.serialize(&mut out)?;
-        self.min_value.serialize(&mut out)?;
-        self.max_value.serialize(&mut out)?;
-        self.interpolations.serialize(&mut out)?;
-        write.write_all(&out)?;
-        (out.len() as u32).serialize(write)?;
-        Ok(())
-    }
-
-    fn deserialize<R: Read>(reader: &mut R) -> io::Result<MultiLinearInterpolFooter> {
-        let mut footer = MultiLinearInterpolFooter {
-            num_vals: u64::deserialize(reader)?,
-            min_value: u64::deserialize(reader)?,
-            max_value: u64::deserialize(reader)?,
-            interpolations: Vec::<Function>::deserialize(reader)?,
-        };
-        for (num, interpol) in footer.interpolations.iter_mut().enumerate() {
-            interpol.start_pos = CHUNK_SIZE * num as u64;
-        }
-        Ok(footer)
-    }
-}
-
-#[inline]
-fn get_interpolation_position(doc: u64) -> usize {
-    let index = doc / CHUNK_SIZE;
-    index as usize
-}
-
-#[inline]
-fn get_interpolation_function(doc: u64, interpolations: &[Function]) -> &Function {
-    &interpolations[get_interpolation_position(doc)]
-}
-
-impl FastFieldCodecReader for MultiLinearInterpolFastFieldReader {
-    /// Opens a fast field given a file.
-    fn open_from_bytes(bytes: &[u8]) -> io::Result<Self> {
-        let footer_len: u32 = (&bytes[bytes.len() - 4..]).deserialize()?;
-
-        let (_data, mut footer) = bytes.split_at(bytes.len() - (4 + footer_len) as usize);
-        let footer = MultiLinearInterpolFooter::deserialize(&mut footer)?;
-
-        Ok(MultiLinearInterpolFastFieldReader { footer })
-    }
-
-    #[inline]
-    fn get_u64(&self, doc: u64, data: &[u8]) -> u64 {
-        let interpolation = get_interpolation_function(doc, &self.footer.interpolations);
-        let doc = doc - interpolation.start_pos;
-        let calculated_value =
-            get_calculated_value(interpolation.value_start_pos, doc, interpolation.slope);
-        let diff = interpolation
-            .bit_unpacker
-            .get(doc, &data[interpolation.data_start_offset as usize..]);
-        (calculated_value + diff) - interpolation.positive_val_offset
-    }
-
-    #[inline]
-    fn min_value(&self) -> u64 {
-        self.footer.min_value
-    }
-    #[inline]
-    fn max_value(&self) -> u64 {
-        self.footer.max_value
-    }
-}
-
-#[inline]
-fn get_slope(first_val: u64, last_val: u64, num_vals: u64) -> f32 {
-    ((last_val as f64 - first_val as f64) / (num_vals as u64 - 1) as f64) as f32
-}
-
-#[inline]
-fn get_calculated_value(first_val: u64, pos: u64, slope: f32) -> u64 {
-    (first_val as i64 + (pos as f32 * slope) as i64) as u64
-}
-
-/// Same as LinearInterpolFastFieldSerializer, but working on chunks of CHUNK_SIZE elements.
-pub struct MultiLinearInterpolFastFieldSerializer {}
-
-impl FastFieldCodecSerializer for MultiLinearInterpolFastFieldSerializer {
-    const NAME: &'static str = "MultiLinearInterpol";
-    const ID: u8 = 3;
-    /// Creates a new fast field serializer.
-    fn serialize(
-        write: &mut impl Write,
-        fastfield_accessor: &impl FastFieldDataAccess,
-        stats: FastFieldStats,
-        data_iter: impl Iterator<Item = u64>,
-        _data_iter1: impl Iterator<Item = u64>,
-    ) -> io::Result<()> {
-        assert!(stats.min_value <= stats.max_value);
-
-        let first_val = fastfield_accessor.get_val(0);
-        let last_val = fastfield_accessor.get_val(stats.num_vals as u64 - 1);
-
-        let mut first_function = Function {
-            end_pos: stats.num_vals,
-            value_start_pos: first_val,
-            value_end_pos: last_val,
-            ..Default::default()
-        };
-        first_function.calc_slope();
-        let mut interpolations = vec![first_function];
-
-        // Since we potentially apply multiple passes over the data, the data is cached.
-        // Multiple iteration can be expensive (merge with index sorting can add lot of overhead per
-        // iteration)
-        let data = data_iter.collect::<Vec<_>>();
-
-        //// let's split this into chunks of CHUNK_SIZE
-        for data_pos in (0..data.len() as u64).step_by(CHUNK_SIZE as usize).skip(1) {
-            let new_fun = {
-                let current_interpolation = interpolations.last_mut().unwrap();
-                current_interpolation.split(data_pos, data[data_pos as usize])
-            };
-            interpolations.push(new_fun);
-        }
-        // calculate offset and max (-> numbits) for each function
-        for interpolation in &mut interpolations {
-            let mut offset = 0;
-            let mut rel_positive_max = 0;
-            for (pos, actual_value) in data
-                [interpolation.start_pos as usize..interpolation.end_pos as usize]
-                .iter()
-                .cloned()
-                .enumerate()
-            {
-                let calculated_value = get_calculated_value(
-                    interpolation.value_start_pos,
-                    pos as u64,
-                    interpolation.slope,
-                );
-                if calculated_value > actual_value {
-                    // negative value we need to apply an offset
-                    // we ignore negative values in the max value calculation, because negative values
-                    // will be offset to 0
-                    offset = offset.max(calculated_value - actual_value);
-                } else {
-                    //positive value no offset reuqired
-                    rel_positive_max = rel_positive_max.max(actual_value - calculated_value);
-                }
-            }
-
-            interpolation.positive_val_offset = offset;
-            interpolation.num_bits = compute_num_bits(rel_positive_max + offset);
-        }
-        let mut bit_packer = BitPacker::new();
-
-        let write = &mut CountingWriter::wrap(write);
-        for interpolation in &mut interpolations {
-            interpolation.data_start_offset = write.written_bytes();
-            let num_bits = interpolation.num_bits;
-            for (pos, actual_value) in data
-                [interpolation.start_pos as usize..interpolation.end_pos as usize]
-                .iter()
-                .cloned()
-                .enumerate()
-            {
-                let calculated_value = get_calculated_value(
-                    interpolation.value_start_pos,
-                    pos as u64,
-                    interpolation.slope,
-                );
-                let diff = (actual_value + interpolation.positive_val_offset) - calculated_value;
-                bit_packer.write(diff, num_bits, write)?;
-            }
-            bit_packer.flush(write)?;
-        }
-        bit_packer.close(write)?;
-
-        let footer = MultiLinearInterpolFooter {
-            num_vals: stats.num_vals,
-            min_value: stats.min_value,
-            max_value: stats.max_value,
-            interpolations,
-        };
-        footer.serialize(write)?;
-        Ok(())
-    }
-
-    fn is_applicable(
-        _fastfield_accessor: &impl FastFieldDataAccess,
-        stats: FastFieldStats,
-    ) -> bool {
-        if stats.num_vals < 5_000 {
-            return false;
-        }
-        // On serialization the offset is added to the actual value.
-        // We need to make sure this won't run into overflow calculation issues.
-        // For this we take the maximum theroretical offset and add this to the max value.
-        // If this doesn't overflow the algortihm should be fine
-        let theorethical_maximum_offset = stats.max_value - stats.min_value;
-        if stats
-            .max_value
-            .checked_add(theorethical_maximum_offset)
-            .is_none()
-        {
-            return false;
-        }
-        true
-    }
-    /// estimation for linear interpolation is hard because, you don't know
-    /// where the local maxima are for the deviation of the calculated value and
-    /// the offset is also unknown.
-    fn estimate(fastfield_accessor: &impl FastFieldDataAccess, stats: FastFieldStats) -> f32 {
-        let first_val_in_first_block = fastfield_accessor.get_val(0);
-        let last_elem_in_first_chunk = CHUNK_SIZE.min(stats.num_vals);
-        let last_val_in_first_block =
-            fastfield_accessor.get_val(last_elem_in_first_chunk as u64 - 1);
-        let slope = get_slope(
-            first_val_in_first_block,
-            last_val_in_first_block,
-            stats.num_vals,
-        );
-
-        // let's sample at 0%, 5%, 10% .. 95%, 100%, but for the first block only
-        let sample_positions = (0..20)
-            .map(|pos| (last_elem_in_first_chunk as f32 / 100.0 * pos as f32 * 5.0) as usize)
-            .collect::<Vec<_>>();
-
-        let max_distance = sample_positions
-            .iter()
-            .map(|pos| {
-                let calculated_value =
-                    get_calculated_value(first_val_in_first_block, *pos as u64, slope);
-                let actual_value = fastfield_accessor.get_val(*pos as u64);
-                distance(calculated_value, actual_value)
-            })
-            .max()
-            .unwrap();
-
-        // Estimate one block and extrapolate the cost to all blocks.
-        // the theory would be that we don't have the actual max_distance, but we are close within 50%
-        // threshold.
-        // It is multiplied by 2 because in a log case scenario the line would be as much above as
-        // below. So the offset would = max_distance
-        //
-        let relative_max_value = (max_distance as f32 * 1.5) * 2.0;
-
-        let num_bits = compute_num_bits(relative_max_value as u64) as u64 * stats.num_vals as u64
-            // function metadata per block
-            + 29 * (stats.num_vals / CHUNK_SIZE);
-        let num_bits_uncompressed = 64 * stats.num_vals;
-        num_bits as f32 / num_bits_uncompressed as f32
-    }
-}
-
-fn distance<T: Sub<Output = T> + Ord>(x: T, y: T) -> T {
-    if x < y {
-        y - x
-    } else {
-        x - y
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use crate::tests::get_codec_test_data_sets;
-
-    fn create_and_validate(data: &[u64], name: &str) {
-        crate::tests::create_and_validate::<
-            MultiLinearInterpolFastFieldSerializer,
-            MultiLinearInterpolFastFieldReader,
-        >(data, name);
-    }
-
-    #[test]
-    fn test_with_codec_data_sets() {
-        let data_sets = get_codec_test_data_sets();
-        for (mut data, name) in data_sets {
-            create_and_validate(&data, name);
-            data.reverse();
-            create_and_validate(&data, name);
-        }
-    }
-    #[test]
-    fn test_simple() {
-        let data = (10..=20_u64).collect::<Vec<_>>();
-        create_and_validate(&data, "simple monotonically");
-    }
-
-    #[test]
-    fn border_cases_1() {
-        let data = (0..1024).collect::<Vec<_>>();
-        create_and_validate(&data, "border case");
-    }
-    #[test]
-    fn border_case_2() {
-        let data = (0..1025).collect::<Vec<_>>();
-        create_and_validate(&data, "border case");
-    }
-    #[test]
-    fn rand() {
-        for _ in 0..10 {
-            let mut data = (5_000..20_000)
-                .map(|_| rand::random::<u64>() as u64)
-                .collect::<Vec<_>>();
-            create_and_validate(&data, "random");
-
-            data.reverse();
-            create_and_validate(&data, "random");
-        }
-    }
-}

ownedbytes/Cargo.toml

@@ -1,10 +0,0 @@
-[package]
-authors = ["Paul Masurel <paul@quickwit.io>", "Pascal Seitz <pascal@quickwit.io>"]
-name = "ownedbytes"
-version = "0.1.0"
-edition = "2018"
-description = "Expose data as static slice"
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-stable_deref_trait = "1.2.0"

ownedbytes/src/lib.rs

@@ -1,290 +0,0 @@
-use stable_deref_trait::StableDeref;
-use std::convert::TryInto;
-use std::mem;
-use std::ops::{Deref, Range};
-use std::sync::Arc;
-use std::{fmt, io};
-
-/// An OwnedBytes simply wraps an object that owns a slice of data and exposes
-/// this data as a static slice.
-///
-/// The backing object is required to be `StableDeref`.
-#[derive(Clone)]
-pub struct OwnedBytes {
-    data: &'static [u8],
-    box_stable_deref: Arc<dyn Deref<Target = [u8]> + Sync + Send>,
-}
-
-impl OwnedBytes {
-    /// Creates an empty `OwnedBytes`.
-    pub fn empty() -> OwnedBytes {
-        OwnedBytes::new(&[][..])
-    }
-
-    /// Creates an `OwnedBytes` intance given a `StableDeref` object.
-    pub fn new<T: StableDeref + Deref<Target = [u8]> + 'static + Send + Sync>(
-        data_holder: T,
-    ) -> OwnedBytes {
-        let box_stable_deref = Arc::new(data_holder);
-        let bytes: &[u8] = box_stable_deref.as_ref();
-        let data = unsafe { mem::transmute::<_, &'static [u8]>(bytes.deref()) };
-        OwnedBytes {
-            data,
-            box_stable_deref,
-        }
-    }
-
-    /// creates a fileslice that is just a view over a slice of the data.
-    pub fn slice(&self, range: Range<usize>) -> Self {
-        OwnedBytes {
-            data: &self.data[range],
-            box_stable_deref: self.box_stable_deref.clone(),
-        }
-    }
-
-    /// Returns the underlying slice of data.
-    /// `Deref` and `AsRef` are also available.
-    #[inline]
-    pub fn as_slice(&self) -> &[u8] {
-        self.data
-    }
-
-    /// Returns the len of the slice.
-    #[inline]
-    pub fn len(&self) -> usize {
-        self.data.len()
-    }
-
-    /// Splits the OwnedBytes into two OwnedBytes `(left, right)`.
-    ///
-    /// Left will hold `split_len` bytes.
-    ///
-    /// This operation is cheap and does not require to copy any memory.
-    /// On the other hand, both `left` and `right` retain a handle over
-    /// the entire slice of memory. In other words, the memory will only
-    /// be released when both left and right are dropped.
-    pub fn split(self, split_len: usize) -> (OwnedBytes, OwnedBytes) {
-        let right_box_stable_deref = self.box_stable_deref.clone();
-        let left = OwnedBytes {
-            data: &self.data[..split_len],
-            box_stable_deref: self.box_stable_deref,
-        };
-        let right = OwnedBytes {
-            data: &self.data[split_len..],
-            box_stable_deref: right_box_stable_deref,
-        };
-        (left, right)
-    }
-
-    /// Returns true iff this `OwnedBytes` is empty.
-    #[inline]
-    pub fn is_empty(&self) -> bool {
-        self.as_slice().is_empty()
-    }
-
-    /// Drops the left most `advance_len` bytes.
-    ///
-    /// See also [.clip(clip_len: usize))](#method.clip).
-    #[inline]
-    pub fn advance(&mut self, advance_len: usize) {
-        self.data = &self.data[advance_len..]
-    }
-
-    /// Reads an `u8` from the `OwnedBytes` and advance by one byte.
-    #[inline]
-    pub fn read_u8(&mut self) -> u8 {
-        assert!(!self.is_empty());
-
-        let byte = self.as_slice()[0];
-        self.advance(1);
-        byte
-    }
-
-    /// Reads an `u64` encoded as little-endian from the `OwnedBytes` and advance by 8 bytes.
-    #[inline]
-    pub fn read_u64(&mut self) -> u64 {
-        assert!(self.len() > 7);
-
-        let octlet: [u8; 8] = self.as_slice()[..8].try_into().unwrap();
-        self.advance(8);
-        u64::from_le_bytes(octlet)
-    }
-}
-
-impl fmt::Debug for OwnedBytes {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        // We truncate the bytes in order to make sure the debug string
-        // is not too long.
-        let bytes_truncated: &[u8] = if self.len() > 8 {
-            &self.as_slice()[..10]
-        } else {
-            self.as_slice()
-        };
-        write!(f, "OwnedBytes({:?}, len={})", bytes_truncated, self.len())
-    }
-}
-
-impl Deref for OwnedBytes {
-    type Target = [u8];
-
-    #[inline]
-    fn deref(&self) -> &Self::Target {
-        self.as_slice()
-    }
-}
-
-impl io::Read for OwnedBytes {
-    #[inline]
-    fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> {
-        let read_len = {
-            let data = self.as_slice();
-            if data.len() >= buf.len() {
-                let buf_len = buf.len();
-                buf.copy_from_slice(&data[..buf_len]);
-                buf.len()
-            } else {
-                let data_len = data.len();
-                buf[..data_len].copy_from_slice(data);
-                data_len
-            }
-        };
-        self.advance(read_len);
-        Ok(read_len)
-    }
-    #[inline]
-    fn read_to_end(&mut self, buf: &mut Vec<u8>) -> io::Result<usize> {
-        let read_len = {
-            let data = self.as_slice();
-            buf.extend(data);
-            data.len()
-        };
-        self.advance(read_len);
-        Ok(read_len)
-    }
-    #[inline]
-    fn read_exact(&mut self, buf: &mut [u8]) -> io::Result<()> {
-        let read_len = self.read(buf)?;
-        if read_len != buf.len() {
-            return Err(io::Error::new(
-                io::ErrorKind::UnexpectedEof,
-                "failed to fill whole buffer",
-            ));
-        }
-        Ok(())
-    }
-}
-
-impl AsRef<[u8]> for OwnedBytes {
-    #[inline]
-    fn as_ref(&self) -> &[u8] {
-        self.as_slice()
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use std::io::{self, Read};
-
-    use super::OwnedBytes;
-
-    #[test]
-    fn test_owned_bytes_debug() {
-        let short_bytes = OwnedBytes::new(b"abcd".as_ref());
-        assert_eq!(
-            format!("{:?}", short_bytes),
-            "OwnedBytes([97, 98, 99, 100], len=4)"
-        );
-        let long_bytes = OwnedBytes::new(b"abcdefghijklmnopq".as_ref());
-        assert_eq!(
-            format!("{:?}", long_bytes),
-            "OwnedBytes([97, 98, 99, 100, 101, 102, 103, 104, 105, 106], len=17)"
-        );
-    }
-
-    #[test]
-    fn test_owned_bytes_read() -> io::Result<()> {
-        let mut bytes = OwnedBytes::new(b"abcdefghiklmnopqrstuvwxyz".as_ref());
-        {
-            let mut buf = [0u8; 5];
-            bytes.read_exact(&mut buf[..]).unwrap();
-            assert_eq!(&buf, b"abcde");
-            assert_eq!(bytes.as_slice(), b"fghiklmnopqrstuvwxyz")
-        }
-        {
-            let mut buf = [0u8; 2];
-            bytes.read_exact(&mut buf[..]).unwrap();
-            assert_eq!(&buf, b"fg");
-            assert_eq!(bytes.as_slice(), b"hiklmnopqrstuvwxyz")
-        }
-        Ok(())
-    }
-
-    #[test]
-    fn test_owned_bytes_read_right_at_the_end() -> io::Result<()> {
-        let mut bytes = OwnedBytes::new(b"abcde".as_ref());
-        let mut buf = [0u8; 5];
-        assert_eq!(bytes.read(&mut buf[..]).unwrap(), 5);
-        assert_eq!(&buf, b"abcde");
-        assert_eq!(bytes.as_slice(), b"");
-        assert_eq!(bytes.read(&mut buf[..]).unwrap(), 0);
-        assert_eq!(&buf, b"abcde");
-        Ok(())
-    }
-    #[test]
-    fn test_owned_bytes_read_incomplete() -> io::Result<()> {
-        let mut bytes = OwnedBytes::new(b"abcde".as_ref());
-        let mut buf = [0u8; 7];
-        assert_eq!(bytes.read(&mut buf[..]).unwrap(), 5);
-        assert_eq!(&buf[..5], b"abcde");
-        assert_eq!(bytes.read(&mut buf[..]).unwrap(), 0);
-        Ok(())
-    }
-
-    #[test]
-    fn test_owned_bytes_read_to_end() -> io::Result<()> {
-        let mut bytes = OwnedBytes::new(b"abcde".as_ref());
-        let mut buf = Vec::new();
-        bytes.read_to_end(&mut buf)?;
-        assert_eq!(buf.as_slice(), b"abcde".as_ref());
-        Ok(())
-    }
-
-    #[test]
-    fn test_owned_bytes_read_u8() -> io::Result<()> {
-        let mut bytes = OwnedBytes::new(b"\xFF".as_ref());
-        assert_eq!(bytes.read_u8(), 255);
-        assert_eq!(bytes.len(), 0);
-        Ok(())
-    }
-
-    #[test]
-    fn test_owned_bytes_read_u64() -> io::Result<()> {
-        let mut bytes = OwnedBytes::new(b"\0\xFF\xFF\xFF\xFF\xFF\xFF\xFF".as_ref());
-        assert_eq!(bytes.read_u64(), u64::MAX - 255);
-        assert_eq!(bytes.len(), 0);
-        Ok(())
-    }
-
-    #[test]
-    fn test_owned_bytes_split() {
-        let bytes = OwnedBytes::new(b"abcdefghi".as_ref());
-        let (left, right) = bytes.split(3);
-        assert_eq!(left.as_slice(), b"abc");
-        assert_eq!(right.as_slice(), b"defghi");
-    }
-
-    #[test]
-    fn test_owned_bytes_split_boundary() {
-        let bytes = OwnedBytes::new(b"abcdefghi".as_ref());
-        {
-            let (left, right) = bytes.clone().split(0);
-            assert_eq!(left.as_slice(), b"");
-            assert_eq!(right.as_slice(), b"abcdefghi");
-        }
-        {
-            let (left, right) = bytes.split(9);
-            assert_eq!(left.as_slice(), b"abcdefghi");
-            assert_eq!(right.as_slice(), b"");
-        }
-    }
-}

query-grammar/Cargo.toml

@@ -1,18 +0,0 @@
-[package]
-name = "tantivy-query-grammar"
-version = "0.15.0"
-authors = ["Paul Masurel <paul.masurel@gmail.com>"]
-license = "MIT"
-categories = ["database-implementations", "data-structures"]
-description = """Search engine library"""
-documentation = "https://tantivy-search.github.io/tantivy/tantivy/index.html"
-homepage = "https://github.com/tantivy-search/tantivy"
-repository = "https://github.com/tantivy-search/tantivy"
-readme = "README.md"
-keywords = ["search", "information", "retrieval"]
-edition = "2018"
-
-[dependencies]
-combine = {version="4", default-features=false, features=[] }
-once_cell = "1.7.2"
-regex ={ version = "1.5.4", default-features = false, features = ["std"] }

query-grammar/README.md

@@ -1,3 +0,0 @@
-# Tantivy Query Grammar
-
-This crate is used by tantivy to parse queries.

query-grammar/src/lib.rs

@@ -1,15 +0,0 @@
-mod occur;
-mod query_grammar;
-mod user_input_ast;
-use combine::parser::Parser;
-
-pub use crate::occur::Occur;
-use crate::query_grammar::parse_to_ast;
-pub use crate::user_input_ast::{UserInputAst, UserInputBound, UserInputLeaf, UserInputLiteral};
-
-pub struct Error;
-
-pub fn parse_query(query: &str) -> Result<UserInputAst, Error> {
-    let (user_input_ast, _remaining) = parse_to_ast().parse(query).map_err(|_| Error)?;
-    Ok(user_input_ast)
-}

query-grammar/src/occur.rs

@@ -1,72 +0,0 @@
-use std::fmt;
-use std::fmt::Write;
-
-/// Defines whether a term in a query must be present,
-/// should be present or must be not present.
-#[derive(Debug, Clone, Hash, Copy, Eq, PartialEq)]
-pub enum Occur {
-    /// For a given document to be considered for scoring,
-    /// at least one of the document with the Should or the Must
-    /// Occur constraint must be within the document.
-    Should,
-    /// Document without the term are excluded from the search.
-    Must,
-    /// Document that contain the term are excluded from the
-    /// search.
-    MustNot,
-}
-
-impl Occur {
-    /// Returns the one-char prefix symbol for this `Occur`.
-    /// - `Should` => '?',
-    /// - `Must` => '+'
-    /// - `Not` => '-'
-    fn to_char(self) -> char {
-        match self {
-            Occur::Should => '?',
-            Occur::Must => '+',
-            Occur::MustNot => '-',
-        }
-    }
-
-    /// Compose two occur values.
-    pub fn compose(left: Occur, right: Occur) -> Occur {
-        match (left, right) {
-            (Occur::Should, _) => right,
-            (Occur::Must, Occur::MustNot) => Occur::MustNot,
-            (Occur::Must, _) => Occur::Must,
-            (Occur::MustNot, Occur::MustNot) => Occur::Must,
-            (Occur::MustNot, _) => Occur::MustNot,
-        }
-    }
-}
-
-impl fmt::Display for Occur {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        f.write_char(self.to_char())
-    }
-}
-
-#[cfg(test)]
-mod test {
-    use crate::Occur;
-
-    #[test]
-    fn test_occur_compose() {
-        assert_eq!(Occur::compose(Occur::Should, Occur::Should), Occur::Should);
-        assert_eq!(Occur::compose(Occur::Should, Occur::Must), Occur::Must);
-        assert_eq!(
-            Occur::compose(Occur::Should, Occur::MustNot),
-            Occur::MustNot
-        );
-        assert_eq!(Occur::compose(Occur::Must, Occur::Should), Occur::Must);
-        assert_eq!(Occur::compose(Occur::Must, Occur::Must), Occur::Must);
-        assert_eq!(Occur::compose(Occur::Must, Occur::MustNot), Occur::MustNot);
-        assert_eq!(
-            Occur::compose(Occur::MustNot, Occur::Should),
-            Occur::MustNot
-        );
-        assert_eq!(Occur::compose(Occur::MustNot, Occur::Must), Occur::MustNot);
-        assert_eq!(Occur::compose(Occur::MustNot, Occur::MustNot), Occur::Must);
-    }
-}

query-grammar/src/query_grammar.rs

@@ -1,693 +0,0 @@
-use super::user_input_ast::{UserInputAst, UserInputBound, UserInputLeaf, UserInputLiteral};
-use crate::Occur;
-use combine::parser::char::{char, digit, space, spaces, string};
-use combine::parser::range::{take_while, take_while1};
-use combine::parser::repeat::escaped;
-use combine::parser::Parser;
-use combine::{
-    attempt, choice, eof, many, many1, one_of, optional, parser, satisfy, skip_many1, value,
-};
-use combine::{error::StringStreamError, parser::combinator::recognize};
-use once_cell::sync::Lazy;
-use regex::Regex;
-
-// Note: '-' char is only forbidden at the beginning of a field name, would be clearer to add it to special characters.
-const SPECIAL_CHARS: &[char] = &[
-    '+', '^', '`', ':', '{', '}', '"', '[', ']', '(', ')', '~', '!', '\\', '*', ' ',
-];
-const ESCAPED_SPECIAL_CHARS_PATTERN: &str = r#"\\(\+|\^|`|:|\{|\}|"|\[|\]|\(|\)|\~|!|\\|\*| )"#;
-
-/// Parses a field_name
-/// A field name must have at least one character and be followed by a colon.
-/// All characters are allowed including special characters `SPECIAL_CHARS`, but these
-/// need to be escaped with a backslack character '\'.
-fn field_name<'a>() -> impl Parser<&'a str, Output = String> {
-    static ESCAPED_SPECIAL_CHARS_RE: Lazy<Regex> =
-        Lazy::new(|| Regex::new(ESCAPED_SPECIAL_CHARS_PATTERN).unwrap());
-
-    recognize::<String, _, _>(escaped(
-        (
-            take_while1(|c| !SPECIAL_CHARS.contains(&c) && c != '-'),
-            take_while(|c| !SPECIAL_CHARS.contains(&c)),
-        ),
-        '\\',
-        satisfy(|c| SPECIAL_CHARS.contains(&c)),
-    ))
-    .skip(char(':'))
-    .map(|s| ESCAPED_SPECIAL_CHARS_RE.replace_all(&s, "$1").to_string())
-    .and_then(|s: String| match s.is_empty() {
-        true => Err(StringStreamError::UnexpectedParse),
-        _ => Ok(s),
-    })
-}
-
-fn word<'a>() -> impl Parser<&'a str, Output = String> {
-    (
-        satisfy(|c: char| {
-            !c.is_whitespace()
-                && !['-', '^', '`', ':', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
-        }),
-        many(satisfy(|c: char| {
-            !c.is_whitespace() && ![':', '^', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
-        })),
-    )
-        .map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
-        .and_then(|s: String| match s.as_str() {
-            "OR" | "AND " | "NOT" => Err(StringStreamError::UnexpectedParse),
-            _ => Ok(s),
-        })
-}
-
-/// Parses a date time according to rfc3339
-/// 2015-08-02T18:54:42+02
-/// 2021-04-13T19:46:26.266051969+00:00
-///
-/// NOTE: also accepts 999999-99-99T99:99:99.266051969+99:99
-/// We delegate rejecting such invalid dates to the logical AST compuation code
-/// which invokes chrono::DateTime::parse_from_rfc3339 on the value to actually parse
-/// it (instead of merely extracting the datetime value as string as done here).
-fn date_time<'a>() -> impl Parser<&'a str, Output = String> {
-    let two_digits = || recognize::<String, _, _>((digit(), digit()));
-
-    // Parses a time zone
-    // -06:30
-    // Z
-    let time_zone = {
-        let utc = recognize::<String, _, _>(char('Z'));
-        let offset = recognize((
-            choice([char('-'), char('+')]),
-            two_digits(),
-            char(':'),
-            two_digits(),
-        ));
-
-        utc.or(offset)
-    };
-
-    // Parses a date
-    // 2010-01-30
-    let date = {
-        recognize::<String, _, _>((
-            many1::<String, _, _>(digit()),
-            char('-'),
-            two_digits(),
-            char('-'),
-            two_digits(),
-        ))
-    };
-
-    // Parses a time
-    // 12:30:02
-    // 19:46:26.266051969
-    let time = {
-        recognize::<String, _, _>((
-            two_digits(),
-            char(':'),
-            two_digits(),
-            char(':'),
-            two_digits(),
-            optional((char('.'), many1::<String, _, _>(digit()))),
-            time_zone,
-        ))
-    };
-
-    recognize((date, char('T'), time))
-}
-
-fn term_val<'a>() -> impl Parser<&'a str, Output = String> {
-    let phrase = char('"').with(many1(satisfy(|c| c != '"'))).skip(char('"'));
-    phrase.or(word())
-}
-
-fn term_query<'a>() -> impl Parser<&'a str, Output = UserInputLiteral> {
-    let term_val_with_field = negative_number().or(term_val());
-    (field_name(), term_val_with_field).map(|(field_name, phrase)| UserInputLiteral {
-        field_name: Some(field_name),
-        phrase,
-    })
-}
-
-fn literal<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
-    let term_default_field = term_val().map(|phrase| UserInputLiteral {
-        field_name: None,
-        phrase,
-    });
-    attempt(term_query())
-        .or(term_default_field)
-        .map(UserInputLeaf::from)
-}
-
-fn negative_number<'a>() -> impl Parser<&'a str, Output = String> {
-    (
-        char('-'),
-        many1(digit()),
-        optional((char('.'), many1(digit()))),
-    )
-        .map(|(s1, s2, s3): (char, String, Option<(char, String)>)| {
-            if let Some(('.', s3)) = s3 {
-                format!("{}{}.{}", s1, s2, s3)
-            } else {
-                format!("{}{}", s1, s2)
-            }
-        })
-}
-
-fn spaces1<'a>() -> impl Parser<&'a str, Output = ()> {
-    skip_many1(space())
-}
-
-/// Function that parses a range out of a Stream
-/// Supports ranges like:
-/// [5 TO 10], {5 TO 10}, [* TO 10], [10 TO *], {10 TO *], >5, <=10
-/// [a TO *], [a TO c], [abc TO bcd}
-fn range<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
-    let range_term_val = || {
-        attempt(date_time())
-            .or(word())
-            .or(negative_number())
-            .or(char('*').with(value("*".to_string())))
-    };
-
-    // check for unbounded range in the form of <5, <=10, >5, >=5
-    let elastic_unbounded_range = (
-        choice([
-            attempt(string(">=")),
-            attempt(string("<=")),
-            attempt(string("<")),
-            attempt(string(">")),
-        ])
-        .skip(spaces()),
-        range_term_val(),
-    )
-        .map(
-            |(comparison_sign, bound): (&str, String)| match comparison_sign {
-                ">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
-                "<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
-                "<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
-                ">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
-                // default case
-                _ => (UserInputBound::Unbounded, UserInputBound::Unbounded),
-            },
-        );
-    let lower_bound = (one_of("{[".chars()), range_term_val()).map(
-        |(boundary_char, lower_bound): (char, String)| {
-            if lower_bound == "*" {
-                UserInputBound::Unbounded
-            } else if boundary_char == '{' {
-                UserInputBound::Exclusive(lower_bound)
-            } else {
-                UserInputBound::Inclusive(lower_bound)
-            }
-        },
-    );
-    let upper_bound = (range_term_val(), one_of("}]".chars())).map(
-        |(higher_bound, boundary_char): (String, char)| {
-            if higher_bound == "*" {
-                UserInputBound::Unbounded
-            } else if boundary_char == '}' {
-                UserInputBound::Exclusive(higher_bound)
-            } else {
-                UserInputBound::Inclusive(higher_bound)
-            }
-        },
-    );
-    // return only lower and upper
-    let lower_to_upper = (
-        lower_bound.skip((spaces(), string("TO"), spaces())),
-        upper_bound,
-    );
-
-    (
-        optional(field_name()).skip(spaces()),
-        // try elastic first, if it matches, the range is unbounded
-        attempt(elastic_unbounded_range).or(lower_to_upper),
-    )
-        .map(|(field, (lower, upper))|
-             // Construct the leaf from extracted field (optional)
-             // and bounds
-             UserInputLeaf::Range {
-                 field,
-                 lower,
-                 upper
-    })
-}
-
-fn negate(expr: UserInputAst) -> UserInputAst {
-    expr.unary(Occur::MustNot)
-}
-
-fn leaf<'a>() -> impl Parser<&'a str, Output = UserInputAst> {
-    parser(|input| {
-        char('(')
-            .with(ast())
-            .skip(char(')'))
-            .or(char('*').map(|_| UserInputAst::from(UserInputLeaf::All)))
-            .or(attempt(
-                string("NOT").skip(spaces1()).with(leaf()).map(negate),
-            ))
-            .or(attempt(range().map(UserInputAst::from)))
-            .or(literal().map(UserInputAst::from))
-            .parse_stream(input)
-            .into_result()
-    })
-}
-
-fn occur_symbol<'a>() -> impl Parser<&'a str, Output = Occur> {
-    char('-')
-        .map(|_| Occur::MustNot)
-        .or(char('+').map(|_| Occur::Must))
-}
-
-fn occur_leaf<'a>() -> impl Parser<&'a str, Output = (Option<Occur>, UserInputAst)> {
-    (optional(occur_symbol()), boosted_leaf())
-}
-
-fn positive_float_number<'a>() -> impl Parser<&'a str, Output = f64> {
-    (many1(digit()), optional((char('.'), many1(digit())))).map(
-        |(int_part, decimal_part_opt): (String, Option<(char, String)>)| {
-            let mut float_str = int_part;
-            if let Some((chr, decimal_str)) = decimal_part_opt {
-                float_str.push(chr);
-                float_str.push_str(&decimal_str);
-            }
-            float_str.parse::<f64>().unwrap()
-        },
-    )
-}
-
-fn boost<'a>() -> impl Parser<&'a str, Output = f64> {
-    (char('^'), positive_float_number()).map(|(_, boost)| boost)
-}
-
-fn boosted_leaf<'a>() -> impl Parser<&'a str, Output = UserInputAst> {
-    (leaf(), optional(boost())).map(|(leaf, boost_opt)| match boost_opt {
-        Some(boost) if (boost - 1.0).abs() > std::f64::EPSILON => {
-            UserInputAst::Boost(Box::new(leaf), boost)
-        }
-        _ => leaf,
-    })
-}
-
-#[derive(Clone, Copy)]
-enum BinaryOperand {
-    Or,
-    And,
-}
-
-fn binary_operand<'a>() -> impl Parser<&'a str, Output = BinaryOperand> {
-    string("AND")
-        .with(value(BinaryOperand::And))
-        .or(string("OR").with(value(BinaryOperand::Or)))
-}
-
-fn aggregate_binary_expressions(
-    left: UserInputAst,
-    others: Vec<(BinaryOperand, UserInputAst)>,
-) -> UserInputAst {
-    let mut dnf: Vec<Vec<UserInputAst>> = vec![vec![left]];
-    for (operator, operand_ast) in others {
-        match operator {
-            BinaryOperand::And => {
-                if let Some(last) = dnf.last_mut() {
-                    last.push(operand_ast);
-                }
-            }
-            BinaryOperand::Or => {
-                dnf.push(vec![operand_ast]);
-            }
-        }
-    }
-    if dnf.len() == 1 {
-        UserInputAst::and(dnf.into_iter().next().unwrap()) //< safe
-    } else {
-        let conjunctions = dnf.into_iter().map(UserInputAst::and).collect();
-        UserInputAst::or(conjunctions)
-    }
-}
-
-fn operand_leaf<'a>() -> impl Parser<&'a str, Output = (BinaryOperand, UserInputAst)> {
-    (
-        binary_operand().skip(spaces()),
-        boosted_leaf().skip(spaces()),
-    )
-}
-
-pub fn ast<'a>() -> impl Parser<&'a str, Output = UserInputAst> {
-    let boolean_expr = (boosted_leaf().skip(spaces()), many1(operand_leaf()))
-        .map(|(left, right)| aggregate_binary_expressions(left, right));
-    let whitespace_separated_leaves = many1(occur_leaf().skip(spaces().silent())).map(
-        |subqueries: Vec<(Option<Occur>, UserInputAst)>| {
-            if subqueries.len() == 1 {
-                let (occur_opt, ast) = subqueries.into_iter().next().unwrap();
-                match occur_opt.unwrap_or(Occur::Should) {
-                    Occur::Must | Occur::Should => ast,
-                    Occur::MustNot => UserInputAst::Clause(vec![(Some(Occur::MustNot), ast)]),
-                }
-            } else {
-                UserInputAst::Clause(subqueries.into_iter().collect())
-            }
-        },
-    );
-    let expr = attempt(boolean_expr).or(whitespace_separated_leaves);
-    spaces().with(expr).skip(spaces())
-}
-
-pub fn parse_to_ast<'a>() -> impl Parser<&'a str, Output = UserInputAst> {
-    spaces()
-        .with(optional(ast()).skip(eof()))
-        .map(|opt_ast| opt_ast.unwrap_or_else(UserInputAst::empty_query))
-}
-
-#[cfg(test)]
-mod test {
-
-    type TestParseResult = Result<(), StringStreamError>;
-
-    use super::*;
-    use combine::parser::Parser;
-
-    pub fn nearly_equals(a: f64, b: f64) -> bool {
-        (a - b).abs() < 0.0005 * (a + b).abs()
-    }
-
-    fn assert_nearly_equals(expected: f64, val: f64) {
-        assert!(
-            nearly_equals(val, expected),
-            "Got {}, expected {}.",
-            val,
-            expected
-        );
-    }
-
-    #[test]
-    fn test_occur_symbol() -> TestParseResult {
-        assert_eq!(super::occur_symbol().parse("-")?, (Occur::MustNot, ""));
-        assert_eq!(super::occur_symbol().parse("+")?, (Occur::Must, ""));
-        Ok(())
-    }
-
-    #[test]
-    fn test_positive_float_number() {
-        fn valid_parse(float_str: &str, expected_val: f64, expected_remaining: &str) {
-            let (val, remaining) = positive_float_number().parse(float_str).unwrap();
-            assert_eq!(remaining, expected_remaining);
-            assert_nearly_equals(val, expected_val);
-        }
-        fn error_parse(float_str: &str) {
-            assert!(positive_float_number().parse(float_str).is_err());
-        }
-        valid_parse("1.0", 1.0, "");
-        valid_parse("1", 1.0, "");
-        valid_parse("0.234234 aaa", 0.234234f64, " aaa");
-        error_parse(".3332");
-        error_parse("1.");
-        error_parse("-1.");
-    }
-
-    #[test]
-    fn test_date_time() {
-        let (val, remaining) = date_time()
-            .parse("2015-08-02T18:54:42+02:30")
-            .expect("cannot parse date");
-        assert_eq!(val, "2015-08-02T18:54:42+02:30");
-        assert_eq!(remaining, "");
-        assert!(date_time().parse("2015-08-02T18:54:42+02").is_err());
-
-        let (val, remaining) = date_time()
-            .parse("2021-04-13T19:46:26.266051969+00:00")
-            .expect("cannot parse fractional date");
-        assert_eq!(val, "2021-04-13T19:46:26.266051969+00:00");
-        assert_eq!(remaining, "");
-    }
-
-    fn test_parse_query_to_ast_helper(query: &str, expected: &str) {
-        let query = parse_to_ast().parse(query).unwrap().0;
-        let query_str = format!("{:?}", query);
-        assert_eq!(query_str, expected);
-    }
-
-    fn test_is_parse_err(query: &str) {
-        assert!(parse_to_ast().parse(query).is_err());
-    }
-
-    #[test]
-    fn test_parse_empty_to_ast() {
-        test_parse_query_to_ast_helper("", "<emptyclause>");
-    }
-
-    #[test]
-    fn test_parse_query_to_ast_hyphen() {
-        test_parse_query_to_ast_helper("\"www-form-encoded\"", "\"www-form-encoded\"");
-        test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
-        test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
-    }
-
-    #[test]
-    fn test_parse_query_to_ast_not_op() {
-        assert_eq!(
-            format!("{:?}", parse_to_ast().parse("NOT")),
-            "Err(UnexpectedParse)"
-        );
-        test_parse_query_to_ast_helper("NOTa", "\"NOTa\"");
-        test_parse_query_to_ast_helper("NOT a", "(-\"a\")");
-    }
-
-    #[test]
-    fn test_boosting() {
-        assert!(parse_to_ast().parse("a^2^3").is_err());
-        assert!(parse_to_ast().parse("a^2^").is_err());
-        test_parse_query_to_ast_helper("a^3", "(\"a\")^3");
-        test_parse_query_to_ast_helper("a^3 b^2", "(*(\"a\")^3 *(\"b\")^2)");
-        test_parse_query_to_ast_helper("a^1", "\"a\"");
-    }
-
-    #[test]
-    fn test_parse_query_to_ast_binary_op() {
-        test_parse_query_to_ast_helper("a AND b", "(+\"a\" +\"b\")");
-        test_parse_query_to_ast_helper("a OR b", "(?\"a\" ?\"b\")");
-        test_parse_query_to_ast_helper("a OR b AND c", "(?\"a\" ?(+\"b\" +\"c\"))");
-        test_parse_query_to_ast_helper("a AND b         AND c", "(+\"a\" +\"b\" +\"c\")");
-        assert_eq!(
-            format!("{:?}", parse_to_ast().parse("a OR b aaa")),
-            "Err(UnexpectedParse)"
-        );
-        assert_eq!(
-            format!("{:?}", parse_to_ast().parse("a AND b aaa")),
-            "Err(UnexpectedParse)"
-        );
-        assert_eq!(
-            format!("{:?}", parse_to_ast().parse("aaa a OR b ")),
-            "Err(UnexpectedParse)"
-        );
-        assert_eq!(
-            format!("{:?}", parse_to_ast().parse("aaa ccc a OR b ")),
-            "Err(UnexpectedParse)"
-        );
-    }
-
-    #[test]
-    fn test_parse_elastic_query_ranges() {
-        test_parse_query_to_ast_helper("title: >a", "\"title\":{\"a\" TO \"*\"}");
-        test_parse_query_to_ast_helper("title:>=a", "\"title\":[\"a\" TO \"*\"}");
-        test_parse_query_to_ast_helper("title: <a", "\"title\":{\"*\" TO \"a\"}");
-        test_parse_query_to_ast_helper("title:<=a", "\"title\":{\"*\" TO \"a\"]");
-        test_parse_query_to_ast_helper("title:<=bsd", "\"title\":{\"*\" TO \"bsd\"]");
-
-        test_parse_query_to_ast_helper("weight: >70", "\"weight\":{\"70\" TO \"*\"}");
-        test_parse_query_to_ast_helper("weight:>=70", "\"weight\":[\"70\" TO \"*\"}");
-        test_parse_query_to_ast_helper("weight: <70", "\"weight\":{\"*\" TO \"70\"}");
-        test_parse_query_to_ast_helper("weight:<=70", "\"weight\":{\"*\" TO \"70\"]");
-        test_parse_query_to_ast_helper("weight: >60.7", "\"weight\":{\"60.7\" TO \"*\"}");
-
-        test_parse_query_to_ast_helper("weight: <= 70", "\"weight\":{\"*\" TO \"70\"]");
-
-        test_parse_query_to_ast_helper("weight: <= 70.5", "\"weight\":{\"*\" TO \"70.5\"]");
-    }
-
-    #[test]
-    fn test_occur_leaf() {
-        let ((occur, ast), _) = super::occur_leaf().parse("+abc").unwrap();
-        assert_eq!(occur, Some(Occur::Must));
-        assert_eq!(format!("{:?}", ast), "\"abc\"");
-    }
-
-    #[test]
-    fn test_field_name() -> TestParseResult {
-        assert_eq!(
-            super::field_name().parse(".my.field.name:a"),
-            Ok((".my.field.name".to_string(), "a"))
-        );
-        assert_eq!(
-            super::field_name().parse("my\\ field\\ name:a"),
-            Ok(("my field name".to_string(), "a"))
-        );
-        assert!(super::field_name().parse("my field:a").is_err());
-        assert_eq!(
-            super::field_name().parse("\\(1\\+1\\):2"),
-            Ok(("(1+1)".to_string(), "2"))
-        );
-        assert_eq!(
-            super::field_name().parse("my_field_name:a"),
-            Ok(("my_field_name".to_string(), "a"))
-        );
-        assert!(super::field_name().parse("my_field_name").is_err());
-        assert!(super::field_name().parse(":a").is_err());
-        assert!(super::field_name().parse("-my_field:a").is_err());
-        assert_eq!(
-            super::field_name().parse("_my_field:a")?,
-            ("_my_field".to_string(), "a")
-        );
-        Ok(())
-    }
-
-    #[test]
-    fn test_field_name_re() {
-        let escaped_special_chars_re = Regex::new(ESCAPED_SPECIAL_CHARS_PATTERN).unwrap();
-        for special_char in SPECIAL_CHARS.iter() {
-            assert_eq!(
-                escaped_special_chars_re.replace_all(&format!("\\{}", special_char), "$1"),
-                special_char.to_string()
-            );
-        }
-    }
-
-    #[test]
-    fn test_range_parser() {
-        // testing the range() parser separately
-        let res = range()
-            .parse("title: <hello")
-            .expect("Cannot parse felxible bound word")
-            .0;
-        let expected = UserInputLeaf::Range {
-            field: Some("title".to_string()),
-            lower: UserInputBound::Unbounded,
-            upper: UserInputBound::Exclusive("hello".to_string()),
-        };
-        let res2 = range()
-            .parse("title:{* TO hello}")
-            .expect("Cannot parse ununbounded to word")
-            .0;
-        assert_eq!(res, expected);
-        assert_eq!(res2, expected);
-
-        let expected_weight = UserInputLeaf::Range {
-            field: Some("weight".to_string()),
-            lower: UserInputBound::Inclusive("71.2".to_string()),
-            upper: UserInputBound::Unbounded,
-        };
-        let res3 = range()
-            .parse("weight: >=71.2")
-            .expect("Cannot parse flexible bound float")
-            .0;
-        let res4 = range()
-            .parse("weight:[71.2 TO *}")
-            .expect("Cannot parse float to unbounded")
-            .0;
-        assert_eq!(res3, expected_weight);
-        assert_eq!(res4, expected_weight);
-
-        let expected_dates = UserInputLeaf::Range {
-            field: Some("date_field".to_string()),
-            lower: UserInputBound::Exclusive("2015-08-02T18:54:42Z".to_string()),
-            upper: UserInputBound::Inclusive("2021-08-02T18:54:42+02:30".to_string()),
-        };
-        let res5 = range()
-            .parse("date_field:{2015-08-02T18:54:42Z TO 2021-08-02T18:54:42+02:30]")
-            .expect("Cannot parse date range")
-            .0;
-        assert_eq!(res5, expected_dates);
-
-        let expected_flexible_dates = UserInputLeaf::Range {
-            field: Some("date_field".to_string()),
-            lower: UserInputBound::Unbounded,
-            upper: UserInputBound::Inclusive("2021-08-02T18:54:42.12345+02:30".to_string()),
-        };
-
-        let res6 = range()
-            .parse("date_field: <=2021-08-02T18:54:42.12345+02:30")
-            .expect("Cannot parse date range")
-            .0;
-        assert_eq!(res6, expected_flexible_dates);
-    }
-
-    #[test]
-    fn test_parse_query_to_triming_spaces() {
-        test_parse_query_to_ast_helper("   abc", "\"abc\"");
-        test_parse_query_to_ast_helper("abc ", "\"abc\"");
-        test_parse_query_to_ast_helper("(  a OR abc)", "(?\"a\" ?\"abc\")");
-        test_parse_query_to_ast_helper("(a  OR abc)", "(?\"a\" ?\"abc\")");
-        test_parse_query_to_ast_helper("(a OR  abc)", "(?\"a\" ?\"abc\")");
-        test_parse_query_to_ast_helper("a OR abc ", "(?\"a\" ?\"abc\")");
-        test_parse_query_to_ast_helper("(a OR abc )", "(?\"a\" ?\"abc\")");
-        test_parse_query_to_ast_helper("(a OR  abc) ", "(?\"a\" ?\"abc\")");
-    }
-
-    #[test]
-    fn test_parse_query_single_term() {
-        test_parse_query_to_ast_helper("abc", "\"abc\"");
-    }
-
-    #[test]
-    fn test_parse_query_default_clause() {
-        test_parse_query_to_ast_helper("a b", "(*\"a\" *\"b\")");
-    }
-
-    #[test]
-    fn test_parse_query_must_default_clause() {
-        test_parse_query_to_ast_helper("+(a b)", "(*\"a\" *\"b\")");
-    }
-
-    #[test]
-    fn test_parse_query_must_single_term() {
-        test_parse_query_to_ast_helper("+d", "\"d\"");
-    }
-
-    #[test]
-    fn test_single_term_with_field() {
-        test_parse_query_to_ast_helper("abc:toto", "\"abc\":\"toto\"");
-    }
-
-    #[test]
-    fn test_single_term_with_float() {
-        test_parse_query_to_ast_helper("abc:1.1", "\"abc\":\"1.1\"");
-        test_parse_query_to_ast_helper("a.b.c:1.1", "\"a.b.c\":\"1.1\"");
-        test_parse_query_to_ast_helper("a\\ b\\ c:1.1", "\"a b c\":\"1.1\"");
-    }
-
-    #[test]
-    fn test_must_clause() {
-        test_parse_query_to_ast_helper("(+a +b)", "(+\"a\" +\"b\")");
-    }
-
-    #[test]
-    fn test_parse_test_query_plus_a_b_plus_d() {
-        test_parse_query_to_ast_helper("+(a b) +d", "(+(*\"a\" *\"b\") +\"d\")");
-    }
-
-    #[test]
-    fn test_parse_test_query_other() {
-        test_parse_query_to_ast_helper("(+a +b) d", "(*(+\"a\" +\"b\") *\"d\")");
-        test_parse_query_to_ast_helper("+abc:toto", "\"abc\":\"toto\"");
-        test_parse_query_to_ast_helper("+a\\+b\\+c:toto", "\"a+b+c\":\"toto\"");
-        test_parse_query_to_ast_helper("(+abc:toto -titi)", "(+\"abc\":\"toto\" -\"titi\")");
-        test_parse_query_to_ast_helper("-abc:toto", "(-\"abc\":\"toto\")");
-        test_is_parse_err("--abc:toto");
-        test_parse_query_to_ast_helper("abc:a b", "(*\"abc\":\"a\" *\"b\")");
-        test_parse_query_to_ast_helper("abc:\"a b\"", "\"abc\":\"a b\"");
-        test_parse_query_to_ast_helper("foo:[1 TO 5]", "\"foo\":[\"1\" TO \"5\"]");
-    }
-
-    #[test]
-    fn test_parse_query_with_range() {
-        test_parse_query_to_ast_helper("[1 TO 5]", "[\"1\" TO \"5\"]");
-        test_parse_query_to_ast_helper("foo:{a TO z}", "\"foo\":{\"a\" TO \"z\"}");
-        test_parse_query_to_ast_helper("foo:[1 TO toto}", "\"foo\":[\"1\" TO \"toto\"}");
-        test_parse_query_to_ast_helper("foo:[* TO toto}", "\"foo\":{\"*\" TO \"toto\"}");
-        test_parse_query_to_ast_helper("foo:[1 TO *}", "\"foo\":[\"1\" TO \"*\"}");
-        test_parse_query_to_ast_helper(
-            "1.2.foo.bar:[1.1 TO *}",
-            "\"1.2.foo.bar\":[\"1.1\" TO \"*\"}",
-        );
-        test_is_parse_err("abc +    ");
-    }
-}

query-grammar/src/user_input_ast.rs

@@ -1,171 +0,0 @@
-use std::fmt;
-use std::fmt::{Debug, Formatter};
-
-use crate::Occur;
-
-#[derive(PartialEq)]
-pub enum UserInputLeaf {
-    Literal(UserInputLiteral),
-    All,
-    Range {
-        field: Option<String>,
-        lower: UserInputBound,
-        upper: UserInputBound,
-    },
-}
-
-impl Debug for UserInputLeaf {
-    fn fmt(&self, formatter: &mut Formatter<'_>) -> Result<(), fmt::Error> {
-        match self {
-            UserInputLeaf::Literal(literal) => literal.fmt(formatter),
-            UserInputLeaf::Range {
-                ref field,
-                ref lower,
-                ref upper,
-            } => {
-                if let Some(ref field) = field {
-                    write!(formatter, "\"{}\":", field)?;
-                }
-                lower.display_lower(formatter)?;
-                write!(formatter, " TO ")?;
-                upper.display_upper(formatter)?;
-                Ok(())
-            }
-            UserInputLeaf::All => write!(formatter, "*"),
-        }
-    }
-}
-
-#[derive(PartialEq)]
-pub struct UserInputLiteral {
-    pub field_name: Option<String>,
-    pub phrase: String,
-}
-
-impl fmt::Debug for UserInputLiteral {
-    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
-        match self.field_name {
-            Some(ref field_name) => write!(formatter, "\"{}\":\"{}\"", field_name, self.phrase),
-            None => write!(formatter, "\"{}\"", self.phrase),
-        }
-    }
-}
-
-#[derive(PartialEq)]
-pub enum UserInputBound {
-    Inclusive(String),
-    Exclusive(String),
-    Unbounded,
-}
-
-impl UserInputBound {
-    fn display_lower(&self, formatter: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
-        match *self {
-            UserInputBound::Inclusive(ref word) => write!(formatter, "[\"{}\"", word),
-            UserInputBound::Exclusive(ref word) => write!(formatter, "{{\"{}\"", word),
-            UserInputBound::Unbounded => write!(formatter, "{{\"*\""),
-        }
-    }
-
-    fn display_upper(&self, formatter: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
-        match *self {
-            UserInputBound::Inclusive(ref word) => write!(formatter, "\"{}\"]", word),
-            UserInputBound::Exclusive(ref word) => write!(formatter, "\"{}\"}}", word),
-            UserInputBound::Unbounded => write!(formatter, "\"*\"}}"),
-        }
-    }
-
-    pub fn term_str(&self) -> &str {
-        match *self {
-            UserInputBound::Inclusive(ref contents) => contents,
-            UserInputBound::Exclusive(ref contents) => contents,
-            UserInputBound::Unbounded => "*",
-        }
-    }
-}
-
-pub enum UserInputAst {
-    Clause(Vec<(Option<Occur>, UserInputAst)>),
-    Leaf(Box<UserInputLeaf>),
-    Boost(Box<UserInputAst>, f64),
-}
-
-impl UserInputAst {
-    pub fn unary(self, occur: Occur) -> UserInputAst {
-        UserInputAst::Clause(vec![(Some(occur), self)])
-    }
-
-    fn compose(occur: Occur, asts: Vec<UserInputAst>) -> UserInputAst {
-        assert_ne!(occur, Occur::MustNot);
-        assert!(!asts.is_empty());
-        if asts.len() == 1 {
-            asts.into_iter().next().unwrap() //< safe
-        } else {
-            UserInputAst::Clause(
-                asts.into_iter()
-                    .map(|ast: UserInputAst| (Some(occur), ast))
-                    .collect::<Vec<_>>(),
-            )
-        }
-    }
-
-    pub fn empty_query() -> UserInputAst {
-        UserInputAst::Clause(Vec::default())
-    }
-
-    pub fn and(asts: Vec<UserInputAst>) -> UserInputAst {
-        UserInputAst::compose(Occur::Must, asts)
-    }
-
-    pub fn or(asts: Vec<UserInputAst>) -> UserInputAst {
-        UserInputAst::compose(Occur::Should, asts)
-    }
-}
-
-impl From<UserInputLiteral> for UserInputLeaf {
-    fn from(literal: UserInputLiteral) -> UserInputLeaf {
-        UserInputLeaf::Literal(literal)
-    }
-}
-
-impl From<UserInputLeaf> for UserInputAst {
-    fn from(leaf: UserInputLeaf) -> UserInputAst {
-        UserInputAst::Leaf(Box::new(leaf))
-    }
-}
-
-fn print_occur_ast(
-    occur_opt: Option<Occur>,
-    ast: &UserInputAst,
-    formatter: &mut fmt::Formatter,
-) -> fmt::Result {
-    if let Some(occur) = occur_opt {
-        write!(formatter, "{}{:?}", occur, ast)?;
-    } else {
-        write!(formatter, "*{:?}", ast)?;
-    }
-    Ok(())
-}
-
-impl fmt::Debug for UserInputAst {
-    fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
-        match *self {
-            UserInputAst::Clause(ref subqueries) => {
-                if subqueries.is_empty() {
-                    write!(formatter, "<emptyclause>")?;
-                } else {
-                    write!(formatter, "(")?;
-                    print_occur_ast(subqueries[0].0, &subqueries[0].1, formatter)?;
-                    for subquery in &subqueries[1..] {
-                        write!(formatter, " ")?;
-                        print_occur_ast(subquery.0, &subquery.1, formatter)?;
-                    }
-                    write!(formatter, ")")?;
-                }
-                Ok(())
-            }
-            UserInputAst::Leaf(ref subquery) => write!(formatter, "{:?}", subquery),
-            UserInputAst::Boost(ref leaf, boost) => write!(formatter, "({:?})^{}", leaf, boost),
-        }
-    }
-}

run-tests.sh

@@ -1,2 +0,0 @@
-#!/bin/bash
-cargo test

src/collector/chained_collector.rs

@@ -0,0 +1,91 @@
+use Result;
+use collector::Collector;
+use SegmentLocalId;
+use SegmentReader;
+use DocId;
+use Score;
+
+/// Collector that does nothing.
+/// This is used in the chain Collector and will hopefully
+/// be optimized away by the compiler.
+pub struct DoNothingCollector;
+impl Collector for DoNothingCollector {
+    #[inline]
+    fn set_segment(&mut self, _: SegmentLocalId, _: &SegmentReader) -> Result<()> {
+        Ok(())
+    }
+    #[inline]
+    fn collect(&mut self, _doc: DocId, _score: Score) {}
+    #[inline]
+    fn requires_scoring(&self) -> bool {
+        false
+    }
+}
+
+/// Zero-cost abstraction used to collect on multiple collectors.
+/// This contraption is only usable if the type of your collectors
+/// are known at compile time.
+pub struct ChainedCollector<Left: Collector, Right: Collector> {
+    left: Left,
+    right: Right,
+}
+
+impl<Left: Collector, Right: Collector> ChainedCollector<Left, Right> {
+    /// Adds a collector
+    pub fn push<C: Collector>(self, new_collector: &mut C) -> ChainedCollector<Self, &mut C> {
+        ChainedCollector {
+            left: self,
+            right: new_collector,
+        }
+    }
+}
+
+impl<Left: Collector, Right: Collector> Collector for ChainedCollector<Left, Right> {
+    fn set_segment(
+        &mut self,
+        segment_local_id: SegmentLocalId,
+        segment: &SegmentReader,
+    ) -> Result<()> {
+        self.left.set_segment(segment_local_id, segment)?;
+        self.right.set_segment(segment_local_id, segment)?;
+        Ok(())
+    }
+
+    fn collect(&mut self, doc: DocId, score: Score) {
+        self.left.collect(doc, score);
+        self.right.collect(doc, score);
+    }
+
+    fn requires_scoring(&self) -> bool {
+        self.left.requires_scoring() || self.right.requires_scoring()
+    }
+}
+
+/// Creates a `ChainedCollector`
+pub fn chain() -> ChainedCollector<DoNothingCollector, DoNothingCollector> {
+    ChainedCollector {
+        left: DoNothingCollector,
+        right: DoNothingCollector,
+    }
+}
+
+#[cfg(test)]
+mod tests {
+
+    use super::*;
+    use collector::{Collector, CountCollector, TopCollector};
+
+    #[test]
+    fn test_chained_collector() {
+        let mut top_collector = TopCollector::with_limit(2);
+        let mut count_collector = CountCollector::default();
+        {
+            let mut collectors = chain().push(&mut top_collector).push(&mut count_collector);
+            collectors.collect(1, 0.2);
+            collectors.collect(2, 0.1);
+            collectors.collect(3, 0.5);
+        }
+        assert_eq!(count_collector.count(), 3);
+        assert!(top_collector.at_capacity());
+    }
+}

src/collector/count_collector.rs

@@ -1,114 +1,54 @@
 use super::Collector;
-use crate::collector::SegmentCollector;
-use crate::DocId;
-use crate::Score;
-use crate::SegmentOrdinal;
-use crate::SegmentReader;
+use DocId;
+use Score;
+use Result;
+use SegmentReader;
+use SegmentLocalId;
 
 /// `CountCollector` collector only counts how many
 /// documents match the query.
-///
-/// ```rust
-/// use tantivy::collector::Count;
-/// use tantivy::query::QueryParser;
-/// use tantivy::schema::{Schema, TEXT};
-/// use tantivy::{doc, Index};
-///
-/// let mut schema_builder = Schema::builder();
-/// let title = schema_builder.add_text_field("title", TEXT);
-/// let schema = schema_builder.build();
-/// let index = Index::create_in_ram(schema);
-///
-/// let mut index_writer = index.writer(3_000_000).unwrap();
-/// index_writer.add_document(doc!(title => "The Name of the Wind"));
-/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
-/// index_writer.add_document(doc!(title => "A Dairy Cow"));
-/// index_writer.add_document(doc!(title => "The Diary of a Young Girl"));
-/// assert!(index_writer.commit().is_ok());
-///
-/// let reader = index.reader().unwrap();
-/// let searcher = reader.searcher();
-///
-/// // Here comes the important part
-/// let query_parser = QueryParser::for_index(&index, vec![title]);
-/// let query = query_parser.parse_query("diary").unwrap();
-/// let count = searcher.search(&query, &Count).unwrap();
-///
-/// assert_eq!(count, 2);
-/// ```
-pub struct Count;
-
-impl Collector for Count {
-    type Fruit = usize;
-
-    type Child = SegmentCountCollector;
-
-    fn for_segment(
-        &self,
-        _: SegmentOrdinal,
-        _: &SegmentReader,
-    ) -> crate::Result<SegmentCountCollector> {
-        Ok(SegmentCountCollector::default())
-    }
-
-    fn requires_scoring(&self) -> bool {
-        false
-    }
-
-    fn merge_fruits(&self, segment_counts: Vec<usize>) -> crate::Result<usize> {
-        Ok(segment_counts.into_iter().sum())
-    }
-}
-
 #[derive(Default)]
-pub struct SegmentCountCollector {
+pub struct CountCollector {
     count: usize,
 }
 
-impl SegmentCollector for SegmentCountCollector {
-    type Fruit = usize;
+impl CountCollector {
+    /// Returns the count of documents that were
+    /// collected.
+    pub fn count(&self) -> usize {
+        self.count
+    }
+}
+
+impl Collector for CountCollector {
+    fn set_segment(&mut self, _: SegmentLocalId, _: &SegmentReader) -> Result<()> {
+        Ok(())
+    }
 
     fn collect(&mut self, _: DocId, _: Score) {
         self.count += 1;
     }
 
-    fn harvest(self) -> usize {
-        self.count
+    fn requires_scoring(&self) -> bool {
+        false
     }
 }
 
 #[cfg(test)]
 mod tests {
-    use super::{Count, SegmentCountCollector};
-    use crate::collector::Collector;
-    use crate::collector::SegmentCollector;
+
+    use collector::{Collector, CountCollector};
 
     #[test]
-    fn test_count_collect_does_not_requires_scoring() {
-        assert!(!Count.requires_scoring());
+    fn test_count_collector() {
+        let mut count_collector = CountCollector::default();
+        assert_eq!(count_collector.count(), 0);
+        count_collector.collect(0u32, 1f32);
+        assert_eq!(count_collector.count(), 1);
+        assert_eq!(count_collector.count(), 1);
+        count_collector.collect(1u32, 1f32);
+        assert_eq!(count_collector.count(), 2);
+        assert!(!count_collector.requires_scoring());
     }
 
-    #[test]
-    fn test_segment_count_collector() {
-        {
-            let count_collector = SegmentCountCollector::default();
-            assert_eq!(count_collector.harvest(), 0);
-        }
-        {
-            let mut count_collector = SegmentCountCollector::default();
-            count_collector.collect(0u32, 1.0);
-            assert_eq!(count_collector.harvest(), 1);
-        }
-        {
-            let mut count_collector = SegmentCountCollector::default();
-            count_collector.collect(0u32, 1.0);
-            assert_eq!(count_collector.harvest(), 1);
-        }
-        {
-            let mut count_collector = SegmentCountCollector::default();
-            count_collector.collect(0u32, 1.0);
-            count_collector.collect(1u32, 1.0);
-            assert_eq!(count_collector.harvest(), 2);
-        }
-    }
 }

src/collector/custom_score_top_collector.rs

@@ -1,123 +0,0 @@
-use crate::collector::top_collector::{TopCollector, TopSegmentCollector};
-use crate::collector::{Collector, SegmentCollector};
-use crate::{DocAddress, DocId, Score, SegmentReader};
-
-pub(crate) struct CustomScoreTopCollector<TCustomScorer, TScore = Score> {
-    custom_scorer: TCustomScorer,
-    collector: TopCollector<TScore>,
-}
-
-impl<TCustomScorer, TScore> CustomScoreTopCollector<TCustomScorer, TScore>
-where
-    TScore: Clone + PartialOrd,
-{
-    pub(crate) fn new(
-        custom_scorer: TCustomScorer,
-        collector: TopCollector<TScore>,
-    ) -> CustomScoreTopCollector<TCustomScorer, TScore> {
-        CustomScoreTopCollector {
-            custom_scorer,
-            collector,
-        }
-    }
-}
-
-/// A custom segment scorer makes it possible to define any kind of score
-/// for a given document belonging to a specific segment.
-///
-/// It is the segment local version of the [`CustomScorer`](./trait.CustomScorer.html).
-pub trait CustomSegmentScorer<TScore>: 'static {
-    /// Computes the score of a specific `doc`.
-    fn score(&mut self, doc: DocId) -> TScore;
-}
-
-/// `CustomScorer` makes it possible to define any kind of score.
-///
-/// The `CustomerScorer` itself does not make much of the computation itself.
-/// Instead, it helps constructing `Self::Child` instances that will compute
-/// the score at a segment scale.
-pub trait CustomScorer<TScore>: Sync {
-    /// Type of the associated [`CustomSegmentScorer`](./trait.CustomSegmentScorer.html).
-    type Child: CustomSegmentScorer<TScore>;
-    /// Builds a child scorer for a specific segment. The child scorer is associated to
-    /// a specific segment.
-    fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child>;
-}
-
-impl<TCustomScorer, TScore> Collector for CustomScoreTopCollector<TCustomScorer, TScore>
-where
-    TCustomScorer: CustomScorer<TScore> + Send + Sync,
-    TScore: 'static + PartialOrd + Clone + Send + Sync,
-{
-    type Fruit = Vec<(TScore, DocAddress)>;
-
-    type Child = CustomScoreTopSegmentCollector<TCustomScorer::Child, TScore>;
-
-    fn for_segment(
-        &self,
-        segment_local_id: u32,
-        segment_reader: &SegmentReader,
-    ) -> crate::Result<Self::Child> {
-        let segment_collector = self.collector.for_segment(segment_local_id, segment_reader);
-        let segment_scorer = self.custom_scorer.segment_scorer(segment_reader)?;
-        Ok(CustomScoreTopSegmentCollector {
-            segment_collector,
-            segment_scorer,
-        })
-    }
-
-    fn requires_scoring(&self) -> bool {
-        false
-    }
-
-    fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> crate::Result<Self::Fruit> {
-        self.collector.merge_fruits(segment_fruits)
-    }
-}
-
-pub struct CustomScoreTopSegmentCollector<T, TScore>
-where
-    TScore: 'static + PartialOrd + Clone + Send + Sync + Sized,
-    T: CustomSegmentScorer<TScore>,
-{
-    segment_collector: TopSegmentCollector<TScore>,
-    segment_scorer: T,
-}
-
-impl<T, TScore> SegmentCollector for CustomScoreTopSegmentCollector<T, TScore>
-where
-    TScore: 'static + PartialOrd + Clone + Send + Sync,
-    T: 'static + CustomSegmentScorer<TScore>,
-{
-    type Fruit = Vec<(TScore, DocAddress)>;
-
-    fn collect(&mut self, doc: DocId, _score: Score) {
-        let score = self.segment_scorer.score(doc);
-        self.segment_collector.collect(doc, score);
-    }
-
-    fn harvest(self) -> Vec<(TScore, DocAddress)> {
-        self.segment_collector.harvest()
-    }
-}
-
-impl<F, TScore, T> CustomScorer<TScore> for F
-where
-    F: 'static + Send + Sync + Fn(&SegmentReader) -> T,
-    T: CustomSegmentScorer<TScore>,
-{
-    type Child = T;
-
-    fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child> {
-        Ok((self)(segment_reader))
-    }
-}
-
-impl<F, TScore> CustomSegmentScorer<TScore> for F
-where
-    F: 'static + FnMut(DocId) -> TScore,
-{
-    fn score(&mut self, doc: DocId) -> TScore {
-        (self)(doc)
-    }
-}

src/collector/docset_collector.rs

@@ -1,61 +0,0 @@
-use std::collections::HashSet;
-
-use crate::{DocAddress, DocId, Score};
-
-use super::{Collector, SegmentCollector};
-
-/// Collectors that returns the set of DocAddress that matches the query.
-///
-/// This collector is mostly useful for tests.
-pub struct DocSetCollector;
-
-impl Collector for DocSetCollector {
-    type Fruit = HashSet<DocAddress>;
-    type Child = DocSetChildCollector;
-
-    fn for_segment(
-        &self,
-        segment_local_id: crate::SegmentOrdinal,
-        _segment: &crate::SegmentReader,
-    ) -> crate::Result<Self::Child> {
-        Ok(DocSetChildCollector {
-            segment_local_id,
-            docs: HashSet::new(),
-        })
-    }
-
-    fn requires_scoring(&self) -> bool {
-        false
-    }
-
-    fn merge_fruits(
-        &self,
-        segment_fruits: Vec<(u32, HashSet<DocId>)>,
-    ) -> crate::Result<Self::Fruit> {
-        let len: usize = segment_fruits.iter().map(|(_, docset)| docset.len()).sum();
-        let mut result = HashSet::with_capacity(len);
-        for (segment_local_id, docs) in segment_fruits {
-            for doc in docs {
-                result.insert(DocAddress::new(segment_local_id, doc));
-            }
-        }
-        Ok(result)
-    }
-}
-
-pub struct DocSetChildCollector {
-    segment_local_id: u32,
-    docs: HashSet<DocId>,
-}
-
-impl SegmentCollector for DocSetChildCollector {
-    type Fruit = (u32, HashSet<DocId>);
-
-    fn collect(&mut self, doc: crate::DocId, _score: Score) {
-        self.docs.insert(doc);
-    }
-
-    fn harvest(self) -> (u32, HashSet<DocId>) {
-        (self.segment_local_id, self.docs)
-    }
-}

src/collector/facet_collector.rs

@@ -1,20 +1,27 @@
-use crate::collector::Collector;
-use crate::collector::SegmentCollector;
-use crate::fastfield::FacetReader;
-use crate::schema::Facet;
-use crate::schema::Field;
-use crate::DocId;
-use crate::Score;
-use crate::SegmentOrdinal;
-use crate::SegmentReader;
-use std::cmp::Ordering;
-use std::collections::btree_map;
+use std::mem;
+use collector::Collector;
+use fastfield::FacetReader;
+use schema::Field;
+use std::cell::UnsafeCell;
+use schema::Facet;
 use std::collections::BTreeMap;
-use std::collections::BTreeSet;
 use std::collections::BinaryHeap;
+use std::collections::Bound;
+use termdict::TermDictionary;
+use termdict::TermStreamer;
+use termdict::TermStreamerBuilder;
+use std::collections::BTreeSet;
+use termdict::TermMerger;
+use docset::SkipResult;
+use std::{usize, u64};
 use std::iter::Peekable;
-use std::ops::Bound;
-use std::{u64, usize};
+
+use DocId;
+use Result;
+use Score;
+use SegmentReader;
+use SegmentLocalId;
+use std::cmp::Ordering;
 
 struct Hit<'a> {
     count: u64,
@@ -24,26 +31,29 @@ struct Hit<'a> {
 impl<'a> Eq for Hit<'a> {}
 
 impl<'a> PartialEq<Hit<'a>> for Hit<'a> {
-    fn eq(&self, other: &Hit<'_>) -> bool {
+    fn eq(&self, other: &Hit) -> bool {
         self.count == other.count
     }
 }
 
 impl<'a> PartialOrd<Hit<'a>> for Hit<'a> {
-    fn partial_cmp(&self, other: &Hit<'_>) -> Option<Ordering> {
+    fn partial_cmp(&self, other: &Hit) -> Option<Ordering> {
         Some(self.cmp(other))
     }
 }
 
 impl<'a> Ord for Hit<'a> {
     fn cmp(&self, other: &Self) -> Ordering {
-        other
-            .count
-            .cmp(&self.count)
-            .then(self.facet.cmp(other.facet))
+        other.count.cmp(&self.count)
     }
 }
 
+struct SegmentFacetCounter {
+    pub facet_reader: FacetReader,
+    pub facet_ords: Vec<u64>,
+    pub facet_counts: Vec<u64>,
+}
+
 fn facet_depth(facet_bytes: &[u8]) -> usize {
     if facet_bytes.is_empty() {
         0
@@ -81,18 +91,21 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
 ///
 ///
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::schema::{Facet, SchemaBuilder, TEXT};
+/// use tantivy::{Index, Result};
 /// use tantivy::collector::FacetCollector;
 /// use tantivy::query::AllQuery;
-/// use tantivy::schema::{Facet, Schema, INDEXED, TEXT};
-/// use tantivy::{doc, Index};
 ///
-/// fn example() -> tantivy::Result<()> {
-///     let mut schema_builder = Schema::builder();
+/// # fn main() { example().unwrap(); }
+/// fn example() -> Result<()> {
+///     let mut schema_builder = SchemaBuilder::new();
 ///
 ///     // Facet have their own specific type.
 ///     // It is not a bad practise to put all of your
 ///     // facet information in the same field.
-///     let facet = schema_builder.add_facet_field("facet", INDEXED);
+///     let facet = schema_builder.add_facet_field("facet");
 ///     let title = schema_builder.add_text_field("title", TEXT);
 ///     let schema = schema_builder.build();
 ///     let index = Index::create_in_ram(schema);
@@ -120,19 +133,23 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
 ///             facet => Facet::from("/lang/en"),
 ///             facet => Facet::from("/category/biography")
 ///         ));
-///         index_writer.commit()?;
+///         index_writer.commit().unwrap();
 ///     }
-///     let reader = index.reader()?;
-///     let searcher = reader.searcher();
+///
+///     index.load_searchers()?;
+///     let searcher = index.searcher();
 ///
 ///     {
-///         let mut facet_collector = FacetCollector::for_field(facet);
+///			let mut facet_collector = FacetCollector::for_field(facet);
 ///         facet_collector.add_facet("/lang");
 ///         facet_collector.add_facet("/category");
-///         let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
+///         searcher.search(&AllQuery, &mut facet_collector).unwrap();
+///
+///         // this object contains count aggregate for all of the facets.
+///         let counts = facet_collector.harvest();
 ///
 ///         // This lists all of the facet counts
-///         let facets: Vec<(&Facet, u64)> = facet_counts
+///         let facets: Vec<(&Facet, u64)> = counts
 ///             .get("/category")
 ///             .collect();
 ///         assert_eq!(facets, vec![
@@ -142,12 +159,15 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
 ///     }
 ///
 ///     {
-///         let mut facet_collector = FacetCollector::for_field(facet);
+///			let mut facet_collector = FacetCollector::for_field(facet);
 ///         facet_collector.add_facet("/category/fiction");
-///         let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
+///         searcher.search(&AllQuery, &mut facet_collector).unwrap();
+///
+///         // this object contains count aggregate for all of the facets.
+///         let counts = facet_collector.harvest();
 ///
 ///         // This lists all of the facet counts
-///         let facets: Vec<(&Facet, u64)> = facet_counts
+///         let facets: Vec<(&Facet, u64)> = counts
 ///             .get("/category/fiction")
 ///             .collect();
 ///         assert_eq!(facets, vec![
@@ -157,13 +177,16 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
 ///         ]);
 ///     }
 ///
-///     {
-///         let mut facet_collector = FacetCollector::for_field(facet);
+///    {
+///			let mut facet_collector = FacetCollector::for_field(facet);
 ///         facet_collector.add_facet("/category/fiction");
-///         let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
+///         searcher.search(&AllQuery, &mut facet_collector).unwrap();
+///
+///         // this object contains count aggregate for all of the facets.
+///         let counts = facet_collector.harvest();
 ///
 ///         // This lists all of the facet counts
-///         let facets: Vec<(&Facet, u64)> = facet_counts.top_k("/category/fiction", 1);
+///         let facets: Vec<(&Facet, u64)> = counts.top_k("/category/fiction", 1);
 ///         assert_eq!(facets, vec![
 ///             (&Facet::from("/category/fiction/fantasy"), 2)
 ///         ]);
@@ -171,27 +194,21 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
 ///
 ///     Ok(())
 /// }
-/// # assert!(example().is_ok());
 /// ```
 pub struct FacetCollector {
+    facet_ords: Vec<u64>,
     field: Field,
-    facets: BTreeSet<Facet>,
-}
+    ff_reader: Option<UnsafeCell<FacetReader>>,
+    segment_counters: Vec<SegmentFacetCounter>,
 
-pub struct FacetSegmentCollector {
-    reader: FacetReader,
-    facet_ords_buf: Vec<u64>,
     // facet_ord -> collapse facet_id
-    collapse_mapping: Vec<usize>,
+    current_segment_collapse_mapping: Vec<usize>,
     // collapse facet_id -> count
-    counts: Vec<u64>,
+    current_segment_counts: Vec<u64>,
     // collapse facet_id -> facet_ord
-    collapse_facet_ords: Vec<u64>,
-}
+    current_collapse_facet_ords: Vec<u64>,
 
-enum SkipResult {
-    Found,
-    NotFound,
+    facets: BTreeSet<Facet>,
 }
 
 fn skip<'a, I: Iterator<Item = &'a Facet>>(
@@ -200,17 +217,17 @@ fn skip<'a, I: Iterator<Item = &'a Facet>>(
 ) -> SkipResult {
     loop {
         match collapse_it.peek() {
-            Some(facet_bytes) => match facet_bytes.encoded_str().as_bytes().cmp(target) {
+            Some(facet_bytes) => match facet_bytes.encoded_bytes().cmp(target) {
                 Ordering::Less => {}
                 Ordering::Greater => {
-                    return SkipResult::NotFound;
+                    return SkipResult::OverStep;
                 }
                 Ordering::Equal => {
-                    return SkipResult::Found;
+                    return SkipResult::Reached;
                 }
             },
             None => {
-                return SkipResult::NotFound;
+                return SkipResult::End;
             }
         }
         collapse_it.next();
@@ -225,8 +242,15 @@ impl FacetCollector {
     /// is of the proper type.
     pub fn for_field(field: Field) -> FacetCollector {
         FacetCollector {
+            facet_ords: Vec::with_capacity(255),
+            segment_counters: Vec::new(),
             field,
-            facets: BTreeSet::default(),
+            ff_reader: None,
+            facets: BTreeSet::new(),
+
+            current_segment_collapse_mapping: Vec::new(),
+            current_collapse_facet_ords: Vec::new(),
+            current_segment_counts: Vec::new(),
         }
     }
 
@@ -256,98 +280,139 @@ impl FacetCollector {
         }
         self.facets.insert(facet);
     }
-}
-
-impl Collector for FacetCollector {
-    type Fruit = FacetCounts;
-
-    type Child = FacetSegmentCollector;
-
-    fn for_segment(
-        &self,
-        _: SegmentOrdinal,
-        reader: &SegmentReader,
-    ) -> crate::Result<FacetSegmentCollector> {
-        let facet_reader = reader.facet_reader(self.field)?;
-
-        let mut collapse_mapping = Vec::new();
-        let mut counts = Vec::new();
-        let mut collapse_facet_ords = Vec::new();
 
+    fn set_collapse_mapping(&mut self, facet_reader: &FacetReader) {
+        self.current_segment_collapse_mapping.clear();
+        self.current_collapse_facet_ords.clear();
+        self.current_segment_counts.clear();
         let mut collapse_facet_it = self.facets.iter().peekable();
-        collapse_facet_ords.push(0);
-        {
-            let mut facet_streamer = facet_reader.facet_dict().range().into_stream()?;
-            if facet_streamer.advance() {
-                'outer: loop {
-                    // at the begining of this loop, facet_streamer
-                    // is positionned on a term that has not been processed yet.
-                    let skip_result = skip(facet_streamer.key(), &mut collapse_facet_it);
-                    match skip_result {
-                        SkipResult::Found => {
-                            // we reach a facet we decided to collapse.
-                            let collapse_depth = facet_depth(facet_streamer.key());
-                            let mut collapsed_id = 0;
-                            collapse_mapping.push(0);
-                            while facet_streamer.advance() {
-                                let depth = facet_depth(facet_streamer.key());
-                                if depth <= collapse_depth {
-                                    continue 'outer;
-                                }
-                                if depth == collapse_depth + 1 {
-                                    collapsed_id = collapse_facet_ords.len();
-                                    collapse_facet_ords.push(facet_streamer.term_ord());
-                                }
-                                collapse_mapping.push(collapsed_id);
-                            }
-                            break;
+        self.current_collapse_facet_ords.push(0);
+        let mut facet_streamer = facet_reader.facet_dict().range().into_stream();
+        if !facet_streamer.advance() {
+            return;
+        }
+        'outer: loop {
+            // at the begining of this loop, facet_streamer
+            // is positionned on a term that has not been processed yet.
+            let skip_result = skip(facet_streamer.key(), &mut collapse_facet_it);
+            match skip_result {
+                SkipResult::Reached => {
+                    // we reach a facet we decided to collapse.
+                    let collapse_depth = facet_depth(facet_streamer.key());
+                    let mut collapsed_id = 0;
+                    self.current_segment_collapse_mapping.push(0);
+                    while facet_streamer.advance() {
+                        let depth = facet_depth(facet_streamer.key());
+                        if depth <= collapse_depth {
+                            continue 'outer;
                         }
-                        SkipResult::NotFound => {
-                            collapse_mapping.push(0);
-                            if !facet_streamer.advance() {
-                                break;
-                            }
+                        if depth == collapse_depth + 1 {
+                            collapsed_id = self.current_collapse_facet_ords.len();
+                            self.current_collapse_facet_ords
+                                .push(facet_streamer.term_ord());
+                            self.current_segment_collapse_mapping.push(collapsed_id);
+                        } else {
+                            self.current_segment_collapse_mapping.push(collapsed_id);
                         }
                     }
+                    break;
+                }
+                SkipResult::End | SkipResult::OverStep => {
+                    self.current_segment_collapse_mapping.push(0);
+                    if !facet_streamer.advance() {
+                        break;
+                    }
                 }
             }
         }
-
-        counts.resize(collapse_facet_ords.len(), 0);
-
-        Ok(FacetSegmentCollector {
-            reader: facet_reader,
-            facet_ords_buf: Vec::with_capacity(255),
-            collapse_mapping,
-            counts,
-            collapse_facet_ords,
-        })
     }
 
-    fn requires_scoring(&self) -> bool {
-        false
+    fn finalize_segment(&mut self) {
+        if self.ff_reader.is_some() {
+            self.segment_counters.push(SegmentFacetCounter {
+                facet_reader: self.ff_reader.take().unwrap().into_inner(),
+                facet_ords: mem::replace(&mut self.current_collapse_facet_ords, Vec::new()),
+                facet_counts: mem::replace(&mut self.current_segment_counts, Vec::new()),
+            });
+        }
     }
 
-    fn merge_fruits(&self, segments_facet_counts: Vec<FacetCounts>) -> crate::Result<FacetCounts> {
-        let mut facet_counts: BTreeMap<Facet, u64> = BTreeMap::new();
-        for segment_facet_counts in segments_facet_counts {
-            for (facet, count) in segment_facet_counts.facet_counts {
-                *(facet_counts.entry(facet).or_insert(0)) += count;
+    /// Returns the results of the collection.
+    ///
+    /// This method does not just return the counters,
+    /// it also translates the facet ordinals of the last segment.
+    pub fn harvest(mut self) -> FacetCounts {
+        self.finalize_segment();
+
+        let collapsed_facet_ords: Vec<&[u64]> = self.segment_counters
+            .iter()
+            .map(|segment_counter| &segment_counter.facet_ords[..])
+            .collect();
+        let collapsed_facet_counts: Vec<&[u64]> = self.segment_counters
+            .iter()
+            .map(|segment_counter| &segment_counter.facet_counts[..])
+            .collect();
+
+        let facet_streams = self.segment_counters
+            .iter()
+            .map(|seg_counts| seg_counts.facet_reader.facet_dict().range().into_stream())
+            .collect::<Vec<_>>();
+
+        let mut facet_merger = TermMerger::new(facet_streams);
+        let mut facet_counts = BTreeMap::new();
+
+        while facet_merger.advance() {
+            let count = facet_merger
+                .current_kvs()
+                .iter()
+                .map(|it| {
+                    let seg_ord = it.segment_ord;
+                    let term_ord = it.streamer.term_ord();
+                    collapsed_facet_ords[seg_ord]
+                        .binary_search(&term_ord)
+                        .map(|collapsed_term_id| {
+                            if collapsed_term_id == 0 {
+                                0
+                            } else {
+                                collapsed_facet_counts[seg_ord][collapsed_term_id]
+                            }
+                        })
+                        .unwrap_or(0)
+                })
+                .sum();
+            if count > 0u64 {
+                let bytes = facet_merger.key().to_owned();
+                facet_counts.insert(Facet::from_encoded(bytes), count);
             }
         }
-        Ok(FacetCounts { facet_counts })
+        FacetCounts { facet_counts }
     }
 }
 
-impl SegmentCollector for FacetSegmentCollector {
-    type Fruit = FacetCounts;
+impl Collector for FacetCollector {
+    fn set_segment(&mut self, _: SegmentLocalId, reader: &SegmentReader) -> Result<()> {
+        self.finalize_segment();
+        let facet_reader = reader.facet_reader(self.field)?;
+        self.set_collapse_mapping(&facet_reader);
+        self.current_segment_counts
+            .resize(self.current_collapse_facet_ords.len(), 0);
+        self.ff_reader = Some(UnsafeCell::new(facet_reader));
+        Ok(())
+    }
 
     fn collect(&mut self, doc: DocId, _: Score) {
-        self.reader.facet_ords(doc, &mut self.facet_ords_buf);
+        let facet_reader: &mut FacetReader = unsafe {
+            &mut *self.ff_reader
+                .as_ref()
+                .expect("collect() was called before set_segment. This should never happen.")
+                .get()
+        };
+        facet_reader.facet_ords(doc, &mut self.facet_ords);
         let mut previous_collapsed_ord: usize = usize::MAX;
-        for &facet_ord in &self.facet_ords_buf {
-            let collapsed_ord = self.collapse_mapping[facet_ord as usize];
-            self.counts[collapsed_ord] += if collapsed_ord == previous_collapsed_ord {
+        for &facet_ord in &self.facet_ords {
+            let collapsed_ord = self.current_segment_collapse_mapping[facet_ord as usize];
+            self.current_segment_counts[collapsed_ord] += if collapsed_ord == previous_collapsed_ord
+            {
                 0
             } else {
                 1
@@ -356,27 +421,8 @@ impl SegmentCollector for FacetSegmentCollector {
         }
     }
 
-    /// Returns the results of the collection.
-    ///
-    /// This method does not just return the counters,
-    /// it also translates the facet ordinals of the last segment.
-    fn harvest(self) -> FacetCounts {
-        let mut facet_counts = BTreeMap::new();
-        let facet_dict = self.reader.facet_dict();
-        for (collapsed_facet_ord, count) in self.counts.iter().cloned().enumerate() {
-            if count == 0 {
-                continue;
-            }
-            let mut facet = vec![];
-            let facet_ord = self.collapse_facet_ords[collapsed_facet_ord];
-            // TODO handle errors.
-            if facet_dict.ord_to_term(facet_ord as u64, &mut facet).is_ok() {
-                if let Ok(facet) = Facet::from_encoded(facet) {
-                    facet_counts.insert(facet, count);
-                }
-            }
-        }
-        FacetCounts { facet_counts }
+    fn requires_scoring(&self) -> bool {
+        false
     }
 }
 
@@ -386,22 +432,9 @@ pub struct FacetCounts {
     facet_counts: BTreeMap<Facet, u64>,
 }
 
-pub struct FacetChildIterator<'a> {
-    underlying: btree_map::Range<'a, Facet, u64>,
-}
-
-impl<'a> Iterator for FacetChildIterator<'a> {
-    type Item = (&'a Facet, u64);
-
-    fn next(&mut self) -> Option<Self::Item> {
-        self.underlying.next().map(|(facet, count)| (facet, *count))
-    }
-}
-
 impl FacetCounts {
-    /// Returns an iterator over all of the facet count pairs inside this result.
-    /// See the documentation for `FacetCollector` for a usage example.
-    pub fn get<T>(&self, facet_from: T) -> FacetChildIterator<'_>
+    #[allow(needless_lifetimes)] //< compiler fails if we remove the lifetime
+    pub fn get<'a, T>(&'a self, facet_from: T) -> impl Iterator<Item = (&'a Facet, u64)>
     where
         Facet: From<T>,
     {
@@ -410,18 +443,17 @@ impl FacetCounts {
         let right_bound = if facet.is_root() {
             Bound::Unbounded
         } else {
-            let mut facet_after_bytes: String = facet.encoded_str().to_owned();
-            facet_after_bytes.push('\u{1}');
-            let facet_after = Facet::from_encoded_string(facet_after_bytes);
+            let mut facet_after_bytes = facet.encoded_bytes().to_owned();
+            facet_after_bytes.push(1u8);
+            let facet_after = Facet::from_encoded(facet_after_bytes);
             Bound::Excluded(facet_after)
         };
-        let underlying: btree_map::Range<'_, _, _> =
-            self.facet_counts.range((left_bound, right_bound));
-        FacetChildIterator { underlying }
+
+        self.facet_counts
+            .range((left_bound, right_bound))
+            .map(|(facet, count)| (facet, *count))
     }
 
-    /// Returns a vector of top `k` facets with their counts, sorted highest-to-lowest by counts.
-    /// See the documentation for `FacetCollector` for a usage example.
     pub fn top_k<T>(&self, facet: T, k: usize) -> Vec<(&Facet, u64)>
     where
         Facet: From<T>,
@@ -429,24 +461,17 @@ impl FacetCounts {
         let mut heap = BinaryHeap::with_capacity(k);
         let mut it = self.get(facet);
 
-        // push the first k elements to first bring the heap
-        // to capacity
         for (facet, count) in (&mut it).take(k) {
             heap.push(Hit { count, facet });
         }
 
-        let mut lowest_count: u64 = heap.peek().map(|hit| hit.count).unwrap_or(u64::MIN); //< the `unwrap_or` case may be triggered but the value
-                                                                                          // is never used in that case.
-
+        let mut lowest_count: u64 = heap.peek().map(|hit| hit.count).unwrap_or(u64::MIN);
         for (facet, count) in it {
             if count > lowest_count {
+                lowest_count = count;
                 if let Some(mut head) = heap.peek_mut() {
                     *head = Hit { count, facet };
                 }
-                // the heap gets reconstructed at this point
-                if let Some(head) = heap.peek() {
-                    lowest_count = head.count;
-                }
             }
         }
         heap.into_sorted_vec()
@@ -458,25 +483,23 @@ impl FacetCounts {
 
 #[cfg(test)]
 mod tests {
+    use test::Bencher;
+    use core::Index;
+    use schema::{Document, Facet, SchemaBuilder};
+    use query::AllQuery;
     use super::{FacetCollector, FacetCounts};
-    use crate::collector::Count;
-    use crate::core::Index;
-    use crate::query::{AllQuery, QueryParser, TermQuery};
-    use crate::schema::{Document, Facet, Field, IndexRecordOption, Schema, INDEXED};
-    use crate::Term;
-    use rand::distributions::Uniform;
-    use rand::prelude::SliceRandom;
-    use rand::{thread_rng, Rng};
     use std::iter;
+    use schema::Field;
+    use rand::{thread_rng, Rng};
 
     #[test]
     fn test_facet_collector_drilldown() {
-        let mut schema_builder = Schema::builder();
-        let facet_field = schema_builder.add_facet_field("facet", INDEXED);
+        let mut schema_builder = SchemaBuilder::new();
+        let facet_field = schema_builder.add_facet_field("facet");
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
 
-        let mut index_writer = index.writer_for_tests().unwrap();
+        let mut index_writer = index.writer(3_000_000).unwrap();
         let num_facets: usize = 3 * 4 * 5;
         let facets: Vec<Facet> = (0..num_facets)
             .map(|mut n| {
@@ -494,12 +517,14 @@ mod tests {
             index_writer.add_document(doc);
         }
         index_writer.commit().unwrap();
-        let reader = index.reader().unwrap();
-        let searcher = reader.searcher();
+        index.load_searchers().unwrap();
+        let searcher = index.searcher();
+
         let mut facet_collector = FacetCollector::for_field(facet_field);
         facet_collector.add_facet(Facet::from("/top1"));
-        let counts = searcher.search(&AllQuery, &facet_collector).unwrap();
+        searcher.search(&AllQuery, &mut facet_collector).unwrap();
 
+        let counts: FacetCounts = facet_collector.harvest();
         {
             let facets: Vec<(String, u64)> = counts
                 .get("/top1")
@@ -512,10 +537,9 @@ mod tests {
                     ("/top1/mid1", 50),
                     ("/top1/mid2", 50),
                     ("/top1/mid3", 50),
-                ]
-                .iter()
-                .map(|&(facet_str, count)| (String::from(facet_str), count))
-                .collect::<Vec<_>>()
+                ].iter()
+                    .map(|&(facet_str, count)| (String::from(facet_str), count))
+                    .collect::<Vec<_>>()
             );
         }
     }
@@ -524,192 +548,66 @@ mod tests {
     #[should_panic(expected = "Tried to add a facet which is a descendant of \
                                an already added facet.")]
     fn test_misused_facet_collector() {
-        let mut facet_collector = FacetCollector::for_field(Field::from_field_id(0));
+        let mut facet_collector = FacetCollector::for_field(Field(0));
         facet_collector.add_facet(Facet::from("/country"));
         facet_collector.add_facet(Facet::from("/country/europe"));
     }
 
-    #[test]
-    fn test_doc_unsorted_multifacet() {
-        let mut schema_builder = Schema::builder();
-        let facet_field = schema_builder.add_facet_field("facets", INDEXED);
-        let schema = schema_builder.build();
-        let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_for_tests().unwrap();
-        index_writer.add_document(doc!(
-            facet_field => Facet::from_text(&"/subjects/A/a").unwrap(),
-            facet_field => Facet::from_text(&"/subjects/B/a").unwrap(),
-            facet_field => Facet::from_text(&"/subjects/A/b").unwrap(),
-            facet_field => Facet::from_text(&"/subjects/B/b").unwrap(),
-        ));
-        index_writer.commit().unwrap();
-        let reader = index.reader().unwrap();
-        let searcher = reader.searcher();
-        assert_eq!(searcher.num_docs(), 1);
-        let mut facet_collector = FacetCollector::for_field(facet_field);
-        facet_collector.add_facet("/subjects");
-        let counts = searcher.search(&AllQuery, &facet_collector).unwrap();
-        let facets: Vec<(&Facet, u64)> = counts.get("/subjects").collect();
-        assert_eq!(facets[0].1, 1);
-    }
-
-    #[test]
-    fn test_doc_search_by_facet() -> crate::Result<()> {
-        let mut schema_builder = Schema::builder();
-        let facet_field = schema_builder.add_facet_field("facet", INDEXED);
-        let schema = schema_builder.build();
-        let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_for_tests()?;
-        index_writer.add_document(doc!(
-            facet_field => Facet::from_text(&"/A/A").unwrap(),
-        ));
-        index_writer.add_document(doc!(
-            facet_field => Facet::from_text(&"/A/B").unwrap(),
-        ));
-        index_writer.add_document(doc!(
-            facet_field => Facet::from_text(&"/A/C/A").unwrap(),
-        ));
-        index_writer.add_document(doc!(
-            facet_field => Facet::from_text(&"/D/C/A").unwrap(),
-        ));
-        index_writer.commit()?;
-        let reader = index.reader()?;
-        let searcher = reader.searcher();
-        assert_eq!(searcher.num_docs(), 4);
-
-        let count_facet = |facet_str: &str| {
-            let term = Term::from_facet(facet_field, &Facet::from_text(facet_str).unwrap());
-            searcher
-                .search(&TermQuery::new(term, IndexRecordOption::Basic), &Count)
-                .unwrap()
-        };
-
-        assert_eq!(count_facet("/"), 4);
-        assert_eq!(count_facet("/A"), 3);
-        assert_eq!(count_facet("/A/B"), 1);
-        assert_eq!(count_facet("/A/C"), 1);
-        assert_eq!(count_facet("/A/C/A"), 1);
-        assert_eq!(count_facet("/C/A"), 0);
-
-        let query_parser = QueryParser::for_index(&index, vec![]);
-        {
-            let query = query_parser.parse_query("facet:/A/B")?;
-            assert_eq!(1, searcher.search(&query, &Count).unwrap());
-        }
-        {
-            let query = query_parser.parse_query("facet:/A")?;
-            assert_eq!(3, searcher.search(&query, &Count)?);
-        }
-        Ok(())
-    }
-
     #[test]
     fn test_non_used_facet_collector() {
-        let mut facet_collector = FacetCollector::for_field(Field::from_field_id(0));
+        let mut facet_collector = FacetCollector::for_field(Field(0));
         facet_collector.add_facet(Facet::from("/country"));
         facet_collector.add_facet(Facet::from("/countryeurope"));
     }
 
     #[test]
     fn test_facet_collector_topk() {
-        let mut schema_builder = Schema::builder();
-        let facet_field = schema_builder.add_facet_field("facet", INDEXED);
+        let mut schema_builder = SchemaBuilder::new();
+        let facet_field = schema_builder.add_facet_field("facet");
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
 
-        let uniform = Uniform::new_inclusive(1, 100_000);
         let mut docs: Vec<Document> = vec![("a", 10), ("b", 100), ("c", 7), ("d", 12), ("e", 21)]
             .into_iter()
             .flat_map(|(c, count)| {
-                let facet = Facet::from(&format!("/facet/{}", c));
+                let facet = Facet::from(&format!("/facet_{}", c));
                 let doc = doc!(facet_field => facet);
                 iter::repeat(doc).take(count)
             })
-            .map(|mut doc| {
-                doc.add_facet(
-                    facet_field,
-                    &format!("/facet/{}", thread_rng().sample(&uniform)),
-                );
-                doc
-            })
             .collect();
-        docs[..].shuffle(&mut thread_rng());
+        thread_rng().shuffle(&mut docs[..]);
 
-        let mut index_writer = index.writer_for_tests().unwrap();
+        let mut index_writer = index.writer(3_000_000).unwrap();
         for doc in docs {
             index_writer.add_document(doc);
         }
         index_writer.commit().unwrap();
-        let searcher = index.reader().unwrap().searcher();
+        index.load_searchers().unwrap();
+
+        let searcher = index.searcher();
 
         let mut facet_collector = FacetCollector::for_field(facet_field);
-        facet_collector.add_facet("/facet");
-        let counts: FacetCounts = searcher.search(&AllQuery, &facet_collector).unwrap();
+        facet_collector.add_facet("/");
+        searcher.search(&AllQuery, &mut facet_collector).unwrap();
 
+        let counts: FacetCounts = facet_collector.harvest();
         {
-            let facets: Vec<(&Facet, u64)> = counts.top_k("/facet", 3);
+            let facets: Vec<(&Facet, u64)> = counts.top_k("/", 3);
             assert_eq!(
                 facets,
                 vec![
-                    (&Facet::from("/facet/b"), 100),
-                    (&Facet::from("/facet/e"), 21),
-                    (&Facet::from("/facet/d"), 12),
+                    (&Facet::from("/facet_b"), 100),
+                    (&Facet::from("/facet_e"), 21),
+                    (&Facet::from("/facet_d"), 12),
                 ]
             );
         }
     }
 
-    #[test]
-    fn test_facet_collector_topk_tie_break() -> crate::Result<()> {
-        let mut schema_builder = Schema::builder();
-        let facet_field = schema_builder.add_facet_field("facet", INDEXED);
-        let schema = schema_builder.build();
-        let index = Index::create_in_ram(schema);
-
-        let docs: Vec<Document> = vec![("b", 2), ("a", 2), ("c", 4)]
-            .into_iter()
-            .flat_map(|(c, count)| {
-                let facet = Facet::from(&format!("/facet/{}", c));
-                let doc = doc!(facet_field => facet);
-                iter::repeat(doc).take(count)
-            })
-            .collect();
-
-        let mut index_writer = index.writer_for_tests()?;
-        for doc in docs {
-            index_writer.add_document(doc);
-        }
-        index_writer.commit()?;
-
-        let searcher = index.reader()?.searcher();
-        let mut facet_collector = FacetCollector::for_field(facet_field);
-        facet_collector.add_facet("/facet");
-        let counts: FacetCounts = searcher.search(&AllQuery, &facet_collector)?;
-
-        let facets: Vec<(&Facet, u64)> = counts.top_k("/facet", 2);
-        assert_eq!(
-            facets,
-            vec![(&Facet::from("/facet/c"), 4), (&Facet::from("/facet/a"), 2)]
-        );
-        Ok(())
-    }
-}
-
-#[cfg(all(test, feature = "unstable"))]
-mod bench {
-
-    use crate::collector::FacetCollector;
-    use crate::query::AllQuery;
-    use crate::schema::{Facet, Schema, INDEXED};
-    use crate::Index;
-    use rand::seq::SliceRandom;
-    use rand::thread_rng;
-    use test::Bencher;
-
     #[bench]
     fn bench_facet_collector(b: &mut Bencher) {
-        let mut schema_builder = Schema::builder();
-        let facet_field = schema_builder.add_facet_field("facet", INDEXED);
+        let mut schema_builder = SchemaBuilder::new();
+        let facet_field = schema_builder.add_facet_field("facet");
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
 
@@ -721,18 +619,19 @@ mod bench {
             }
         }
         // 40425 docs
-        docs[..].shuffle(&mut thread_rng());
+        thread_rng().shuffle(&mut docs[..]);
 
-        let mut index_writer = index.writer_for_tests().unwrap();
+        let mut index_writer = index.writer(3_000_000).unwrap();
         for doc in docs {
             index_writer.add_document(doc);
         }
         index_writer.commit().unwrap();
-        let reader = index.reader().unwrap();
+        index.load_searchers().unwrap();
+
         b.iter(|| {
-            let searcher = reader.searcher();
-            let facet_collector = FacetCollector::for_field(facet_field);
-            searcher.search(&AllQuery, &facet_collector).unwrap();
+            let searcher = index.searcher();
+            let mut facet_collector = FacetCollector::for_field(facet_field);
+            searcher.search(&AllQuery, &mut facet_collector).unwrap();
         });
     }
 }

src/collector/filter_collector_wrapper.rs

@@ -1,183 +0,0 @@
-// # Custom collector example
-//
-// This example shows how you can implement your own
-// collector. As an example, we will compute a collector
-// that computes the standard deviation of a given fast field.
-//
-// Of course, you can have a look at the tantivy's built-in collectors
-// such as the `CountCollector` for more examples.
-
-// ---
-// Importing tantivy...
-use std::marker::PhantomData;
-
-use crate::collector::{Collector, SegmentCollector};
-use crate::fastfield::{DynamicFastFieldReader, FastFieldReader, FastValue};
-use crate::schema::Field;
-use crate::{Score, SegmentReader, TantivyError};
-
-/// The `FilterCollector` collector filters docs using a fast field value and a predicate.
-/// Only the documents for which the predicate returned "true" will be passed on to the next collector.
-///
-/// ```rust
-/// use tantivy::collector::{TopDocs, FilterCollector};
-/// use tantivy::query::QueryParser;
-/// use tantivy::schema::{Schema, TEXT, INDEXED, FAST};
-/// use tantivy::{doc, DocAddress, Index};
-///
-/// let mut schema_builder = Schema::builder();
-/// let title = schema_builder.add_text_field("title", TEXT);
-/// let price = schema_builder.add_u64_field("price", INDEXED | FAST);
-/// let schema = schema_builder.build();
-/// let index = Index::create_in_ram(schema);
-///
-/// let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
-/// index_writer.add_document(doc!(title => "The Name of the Wind", price => 30_200u64));
-/// index_writer.add_document(doc!(title => "The Diary of Muadib", price => 29_240u64));
-/// index_writer.add_document(doc!(title => "A Dairy Cow", price => 21_240u64));
-/// index_writer.add_document(doc!(title => "The Diary of a Young Girl", price => 20_120u64));
-/// assert!(index_writer.commit().is_ok());
-///
-/// let reader = index.reader().unwrap();
-/// let searcher = reader.searcher();
-///
-/// let query_parser = QueryParser::for_index(&index, vec![title]);
-/// let query = query_parser.parse_query("diary").unwrap();
-/// let no_filter_collector = FilterCollector::new(price, &|value: u64| value > 20_120u64, TopDocs::with_limit(2));
-/// let top_docs = searcher.search(&query, &no_filter_collector).unwrap();
-///
-/// assert_eq!(top_docs.len(), 1);
-/// assert_eq!(top_docs[0].1, DocAddress::new(0, 1));
-///
-/// let filter_all_collector: FilterCollector<_, _, u64> = FilterCollector::new(price, &|value| value < 5u64, TopDocs::with_limit(2));
-/// let filtered_top_docs = searcher.search(&query, &filter_all_collector).unwrap();
-///
-/// assert_eq!(filtered_top_docs.len(), 0);
-/// ```
-pub struct FilterCollector<TCollector, TPredicate, TPredicateValue: FastValue>
-where
-    TPredicate: 'static + Clone,
-{
-    field: Field,
-    collector: TCollector,
-    predicate: TPredicate,
-    t_predicate_value: PhantomData<TPredicateValue>,
-}
-
-impl<TCollector, TPredicate, TPredicateValue: FastValue>
-    FilterCollector<TCollector, TPredicate, TPredicateValue>
-where
-    TCollector: Collector + Send + Sync,
-    TPredicate: Fn(TPredicateValue) -> bool + Send + Sync + Clone,
-{
-    /// Create a new FilterCollector.
-    pub fn new(
-        field: Field,
-        predicate: TPredicate,
-        collector: TCollector,
-    ) -> FilterCollector<TCollector, TPredicate, TPredicateValue> {
-        FilterCollector {
-            field,
-            predicate,
-            collector,
-            t_predicate_value: PhantomData,
-        }
-    }
-}
-
-impl<TCollector, TPredicate, TPredicateValue: FastValue> Collector
-    for FilterCollector<TCollector, TPredicate, TPredicateValue>
-where
-    TCollector: Collector + Send + Sync,
-    TPredicate: 'static + Fn(TPredicateValue) -> bool + Send + Sync + Clone,
-    TPredicateValue: FastValue,
-{
-    // That's the type of our result.
-    // Our standard deviation will be a float.
-    type Fruit = TCollector::Fruit;
-
-    type Child = FilterSegmentCollector<TCollector::Child, TPredicate, TPredicateValue>;
-
-    fn for_segment(
-        &self,
-        segment_local_id: u32,
-        segment_reader: &SegmentReader,
-    ) -> crate::Result<FilterSegmentCollector<TCollector::Child, TPredicate, TPredicateValue>> {
-        let schema = segment_reader.schema();
-        let field_entry = schema.get_field_entry(self.field);
-        if !field_entry.is_fast() {
-            return Err(TantivyError::SchemaError(format!(
-                "Field {:?} is not a fast field.",
-                field_entry.name()
-            )));
-        }
-        let requested_type = TPredicateValue::to_type();
-        let field_schema_type = field_entry.field_type().value_type();
-        if requested_type != field_schema_type {
-            return Err(TantivyError::SchemaError(format!(
-                "Field {:?} is of type {:?}!={:?}",
-                field_entry.name(),
-                requested_type,
-                field_schema_type
-            )));
-        }
-
-        let fast_field_reader = segment_reader
-            .fast_fields()
-            .typed_fast_field_reader(self.field)?;
-
-        let segment_collector = self
-            .collector
-            .for_segment(segment_local_id, segment_reader)?;
-
-        Ok(FilterSegmentCollector {
-            fast_field_reader,
-            segment_collector,
-            predicate: self.predicate.clone(),
-            t_predicate_value: PhantomData,
-        })
-    }
-
-    fn requires_scoring(&self) -> bool {
-        self.collector.requires_scoring()
-    }
-
-    fn merge_fruits(
-        &self,
-        segment_fruits: Vec<<TCollector::Child as SegmentCollector>::Fruit>,
-    ) -> crate::Result<TCollector::Fruit> {
-        self.collector.merge_fruits(segment_fruits)
-    }
-}
-
-pub struct FilterSegmentCollector<TSegmentCollector, TPredicate, TPredicateValue>
-where
-    TPredicate: 'static,
-    TPredicateValue: FastValue,
-{
-    fast_field_reader: DynamicFastFieldReader<TPredicateValue>,
-    segment_collector: TSegmentCollector,
-    predicate: TPredicate,
-    t_predicate_value: PhantomData<TPredicateValue>,
-}
-
-impl<TSegmentCollector, TPredicate, TPredicateValue> SegmentCollector
-    for FilterSegmentCollector<TSegmentCollector, TPredicate, TPredicateValue>
-where
-    TSegmentCollector: SegmentCollector,
-    TPredicate: 'static + Fn(TPredicateValue) -> bool + Send + Sync,
-    TPredicateValue: FastValue,
-{
-    type Fruit = TSegmentCollector::Fruit;
-
-    fn collect(&mut self, doc: u32, score: Score) {
-        let value = self.fast_field_reader.get(doc);
-        if (self.predicate)(value) {
-            self.segment_collector.collect(doc, score)
-        }
-    }
-
-    fn harvest(self) -> <TSegmentCollector as SegmentCollector>::Fruit {
-        self.segment_collector.harvest()
-    }
-}