From b8f32d082fb0b8da096c34c95a31394a5ae80e6a Mon Sep 17 00:00:00 2001
From: Tevin Wang <tevin@cmu.edu>
Date: Wed, 23 Aug 2023 19:00:37 -0700
Subject: [PATCH] Clean up docs testing - exclude by glob instead of by file
 (#450)

---
 docs/test/md_testing.js | 14 ++++++--------
 docs/test/md_testing.py | 15 ++++++++-------
 2 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/docs/test/md_testing.js b/docs/test/md_testing.js
index faa6a62aa..7f8a6f091 100644
--- a/docs/test/md_testing.js
+++ b/docs/test/md_testing.js
@@ -2,20 +2,17 @@ const glob = require("glob");
 const fs = require("fs");
 const path = require("path");
 
-const excludedFiles = [
+const globString = "../src/**/*.md";
+const excludedGlobs = [
   "../src/fts.md",
   "../src/embedding.md",
-  "../src/ann_indexes.md",
-  "../src/examples/serverless_lancedb_with_s3_and_lambda.md",
-  "../src/examples/serverless_qa_bot_with_modal_and_langchain.md",
-  "../src/examples/transformerjs_embedding_search_nodejs.md",
-  "../src/examples/youtube_transcript_bot_with_nodejs.md",
+  "../src/examples/*.md",
   "../src/guides/tables.md",
 ];
+
 const nodePrefix = "javascript";
 const nodeFile = ".js";
 const nodeFolder = "node";
-const globString = "../src/**/*.md";
 const asyncPrefix = "(async () => {\n";
 const asyncSuffix = "})();";
 
@@ -34,6 +31,7 @@ function* yieldLines(lines, prefix, suffix) {
 }
 
 const files = glob.sync(globString, { recursive: true });
+const excludedFiles = glob.sync(excludedGlobs, { recursive: true });
 
 for (const file of files.filter((file) => !excludedFiles.includes(file))) {
   const lines = [];
@@ -51,4 +49,4 @@ for (const file of files.filter((file) => !excludedFiles.includes(file))) {
     fs.mkdirSync(path.dirname(outPath), { recursive: true });
     fs.writeFileSync(outPath, asyncPrefix + "\n" + lines.join("\n") + asyncSuffix);
   }
-}
+}
\ No newline at end of file
diff --git a/docs/test/md_testing.py b/docs/test/md_testing.py
index d08d9d437..081ab9fde 100644
--- a/docs/test/md_testing.py
+++ b/docs/test/md_testing.py
@@ -2,12 +2,11 @@ import glob
 from typing import Iterator
 from pathlib import Path
 
-excluded_files = [
+glob_string = "../src/**/*.md"
+excluded_globs = [
     "../src/fts.md",
     "../src/embedding.md",
-    "../src/examples/serverless_lancedb_with_s3_and_lambda.md",
-    "../src/examples/serverless_qa_bot_with_modal_and_langchain.md",
-    "../src/examples/youtube_transcript_bot_with_nodejs.md",
+    "../src/examples/*.md",
     "../src/integrations/voxel51.md",
     "../src/guides/tables.md"
 ]
@@ -15,7 +14,9 @@ excluded_files = [
 python_prefix = "py"
 python_file = ".py"
 python_folder = "python"
-glob_string = "../src/**/*.md"
+
+files = glob.glob(glob_string, recursive=True)
+excluded_files = [f for excluded_glob in excluded_globs for f in glob.glob(excluded_glob, recursive=True)]
 
 def yield_lines(lines: Iterator[str], prefix: str, suffix: str):
     in_code_block = False
@@ -31,7 +32,7 @@ def yield_lines(lines: Iterator[str], prefix: str, suffix: str):
         elif in_code_block:
             yield line[strip_length:]
 
-for file in filter(lambda file: file not in excluded_files, glob.glob(glob_string, recursive=True)):
+for file in filter(lambda file: file not in excluded_files, files):
     with open(file, "r") as f:
         lines = list(yield_lines(iter(f), "```", "```"))
 
@@ -40,4 +41,4 @@ for file in filter(lambda file: file not in excluded_files, glob.glob(glob_strin
         print(out_path)
         out_path.parent.mkdir(exist_ok=True, parents=True)
         with open(out_path, "w") as out:
-            out.writelines(lines)
+            out.writelines(lines)
\ No newline at end of file