chore(ci-visibility): improve segments algorithm (#5999)

CI Visibility: Improve segments algorithm so all segments are returned
instead of a single segment covering them.

## Checklist
- [x] Change(s) are motivated and described in the PR description.
- [x] Testing strategy is described if automated tests are not included
in the PR.
- [x] Risk is outlined (performance impact, potential for breakage,
maintainability, etc).
- [x] Change is maintainable (easy to change, telemetry, documentation).
- [x] [Library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/contributing.html#Release-Note-Guidelines)
are followed.
- [x] Documentation is included (in-code, generated user docs, [public
corp docs](https://github.com/DataDog/documentation/)).

## Reviewer Checklist

- [ ] Title is accurate.
- [ ] No unnecessary changes are introduced.
- [ ] Description motivates each change.
- [ ] Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes unless absolutely necessary.
- [ ] Testing strategy adequately addresses listed risk(s).
- [ ] Change is maintainable (easy to change, telemetry, documentation).
- [ ] Release note makes sense to a user of the library.
- [ ] Reviewer has explicitly acknowledged and discussed the performance
implications of this PR as reported in the benchmarks PR comment.

Author: gnufede

ddtrace/internal/ci_visibility/coverage.py

@@ -1,4 +1,5 @@
 import contextlib
+from itertools import groupby
 import json
 import os
 from typing import Iterable
@@ -60,15 +61,16 @@ def cover(span, root=None, **kwargs):
 
 
 def segments(lines):
-    # type: (Iterable[int]) -> Iterable[Tuple[int, int, int, int, int]]
+    # type: (Iterable[int]) -> List[Tuple[int, int, int, int, int]]
     """Extract the relevant report data for a single file."""
-
-    def as_segments(it):
-        # type: (Iterable[int]) -> Tuple[int, int, int, int, int]
-        sequence = list(it)  # type: List[int]
-        return (sequence[0], 0, sequence[-1], 0, -1)
-
-    return [as_segments(sorted(lines))]
+    _segments = []
+    for key, g in groupby(enumerate(sorted(lines)), lambda x: x[1] - x[0]):
+        group = list(g)
+        start = group[0][1]
+        end = group[-1][1]
+        _segments.append((start, 0, end, 0, -1))
+
+    return _segments
 
 
 def _lines(coverage, context):

tests/ci_visibility/test_coverage.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python3
+import pytest
+
+from ddtrace.internal.ci_visibility.coverage import segments
+
+
+@pytest.mark.parametrize(
+    "lines,expected_segments",
+    [
+        ([1, 2, 3, 4, 5, 6, 7, 8, 9, 10], [(1, 0, 10, 0, -1)]),
+        ([1, 2, 4, 5, 6, 7, 8, 9, 10], [(1, 0, 2, 0, -1), (4, 0, 10, 0, -1)]),
+        ([1, 3, 4, 5, 6, 7, 8, 9, 10], [(1, 0, 1, 0, -1), (3, 0, 10, 0, -1)]),
+        ([1, 2, 3, 4, 5, 6, 7, 8, 10], [(1, 0, 8, 0, -1), (10, 0, 10, 0, -1)]),
+        ([1, 2, 3, 4, 10, 5, 6, 7, 8], [(1, 0, 8, 0, -1), (10, 0, 10, 0, -1)]),
+    ],
+)
+def test_segments(lines, expected_segments):
+    assert segments(lines) == expected_segments