From daa79b150f8d81430d9d3aa92c9cdc8c5568e377 Mon Sep 17 00:00:00 2001
From: Alexander Bayandin <alexander@neon.tech>
Date: Tue, 30 May 2023 14:05:41 +0100
Subject: [PATCH] Code Coverage: store lcov report (#4358)

## Problem

In the future, we want to compare code coverage on a PR with coverage on
the main branch.
Currently, we store only code coverage HTML reports, I suggest we start
storing reports in "lcov info" format that we can use/parse in the
future. Currently, the file size is ~7Mb (it's a text-based format and
could be compressed into a ~400Kb archive)

- More about "lcov info" format:
https://manpages.ubuntu.com/manpages/jammy/man1/geninfo.1.html#files
- Part of https://github.com/neondatabase/neon/issues/3543

## Summary of changes
- Change `scripts/coverage` to output lcov coverage to
`report/lcov.info` file instead of stdout (we already upload the whole
`report/` directory to S3)
---
 .github/workflows/build_and_test.yml | 11 ++++++++---
 scripts/coverage                     | 21 +++++++++++++++------
 2 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml
index e00b98250c..b732095f8f 100644
--- a/.github/workflows/build_and_test.yml
+++ b/.github/workflows/build_and_test.yml
@@ -492,19 +492,24 @@ jobs:
         env:
           COMMIT_URL: ${{ github.server_url }}/${{ github.repository }}/commit/${{ github.event.pull_request.head.sha || github.sha }}
         run: |
-          scripts/coverage \
-            --dir=/tmp/coverage report \
+          scripts/coverage --dir=/tmp/coverage \
+            report \
             --input-objects=/tmp/coverage/binaries.list \
             --commit-url=${COMMIT_URL} \
             --format=github
 
+          scripts/coverage --dir=/tmp/coverage \
+            report \
+            --input-objects=/tmp/coverage/binaries.list \
+            --format=lcov
+
       - name: Upload coverage report
         id: upload-coverage-report
         env:
           BUCKET: neon-github-public-dev
           COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
         run: |
-          aws s3 cp --only-show-errors --recursive /tmp/coverage/report s3://neon-github-public-dev/code-coverage/${COMMIT_SHA}
+          aws s3 cp --only-show-errors --recursive /tmp/coverage/report s3://${BUCKET}/code-coverage/${COMMIT_SHA}
 
           REPORT_URL=https://${BUCKET}.s3.amazonaws.com/code-coverage/${COMMIT_SHA}/index.html
           echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
diff --git a/scripts/coverage b/scripts/coverage
index 1dc92e57cc..52a69c93b9 100755
--- a/scripts/coverage
+++ b/scripts/coverage
@@ -156,7 +156,9 @@ class LLVM:
              profdata: Path,
              objects: List[str],
              sources: List[str],
-             demangler: Optional[Path] = None) -> None:
+             demangler: Optional[Path] = None,
+             output_file: Optional[Path] = None,
+             ) -> None:
 
         cwd = self.cargo.cwd
         objects = list(intersperse('-object', objects))
@@ -180,14 +182,18 @@ class LLVM:
             *objects,
             *sources,
         ]
-        subprocess.check_call(cmd, cwd=cwd)
+        if output_file is not None:
+            with output_file.open('w') as outfile:
+                subprocess.check_call(cmd, cwd=cwd, stdout=outfile)
+        else:
+            subprocess.check_call(cmd, cwd=cwd)
 
     def cov_report(self, **kwargs) -> None:
         self._cov(subcommand='report', **kwargs)
 
-    def cov_export(self, *, kind: str, **kwargs) -> None:
+    def cov_export(self, *, kind: str, output_file: Optional[Path], **kwargs) -> None:
         extras = (f'-format={kind}', )
-        self._cov(subcommand='export', *extras, **kwargs)
+        self._cov(subcommand='export', *extras, output_file=output_file, **kwargs)
 
     def cov_show(self, *, kind: str, output_dir: Optional[Path] = None, **kwargs) -> None:
         extras = [f'-format={kind}']
@@ -283,9 +289,12 @@ class TextReport(Report):
         self.llvm.cov_show(kind='text', **self._common_kwargs())
 
 
+@dataclass
 class LcovReport(Report):
+    output_file: Path
+
     def generate(self) -> None:
-        self.llvm.cov_export(kind='lcov', **self._common_kwargs())
+        self.llvm.cov_export(kind='lcov',  output_file=self.output_file, **self._common_kwargs())
 
 
 @dataclass
@@ -475,7 +484,7 @@ class State:
             'text':
             lambda: TextReport(**params),
             'lcov':
-            lambda: LcovReport(**params),
+            lambda: LcovReport(**params, output_file=self.report_dir / 'lcov.info'),
             'summary':
             lambda: SummaryReport(**params),
             'github':