| 1 | #!/usr/bin/env python3 |
| 2 | |
| 3 | import argparse |
| 4 | import re |
| 5 | import subprocess |
| 6 | import sys |
| 7 | from pathlib import Path |
| 8 | |
| 9 | from ruamel.yaml import YAML, YAMLError |
| 10 | |
| 11 | from gen_taxonomy import FATAL, Finding, build_taxonomy, relpath |
| 12 | from _common import REPO_PATH |
| 13 | |
| 14 | HUNK_RE = re.compile(r'^@@ -\d+(?:,\d+)? \+(\d+)(?:,(\d+))? @@') |
| 15 | |
| 16 | |
| 17 | def run_git(*args): |
| 18 | return subprocess.check_output(['git', '-C', str(REPO_PATH), *args], text=True) |
| 19 | |
| 20 | |
| 21 | def metadata_metrics_spans(path): |
| 22 | text = path.read_text() |
| 23 | lines = text.splitlines() |
| 24 | yaml = YAML(typ='rt') |
| 25 | try: |
| 26 | data = yaml.load(text) |
| 27 | except YAMLError: |
| 28 | return [] |
| 29 | |
| 30 | spans = [] |
| 31 | modules = data.get('modules', []) if isinstance(data, dict) else [] |
| 32 | for module_index, module in enumerate(modules): |
| 33 | if not isinstance(module, dict) or 'metrics' not in module: |
| 34 | continue |
| 35 | try: |
| 36 | start = module.lc.key('metrics')[0] + 1 |
| 37 | except (AttributeError, KeyError, TypeError): |
| 38 | continue |
| 39 | |
| 40 | next_lines = [] |
| 41 | for key in module: |
| 42 | if key == 'metrics': |
| 43 | continue |
| 44 | try: |
| 45 | key_line = module.lc.key(key)[0] + 1 |
| 46 | except (AttributeError, KeyError, TypeError): |
| 47 | continue |
| 48 | if key_line > start: |
| 49 | next_lines.append(key_line) |
| 50 | |
| 51 | if next_lines: |
| 52 | end = min(next_lines) - 1 |
| 53 | else: |
| 54 | next_module_line = None |
| 55 | try: |
| 56 | if module_index + 1 < len(modules): |
| 57 | next_module_line = modules.lc.item(module_index + 1)[0] + 1 |
| 58 | except (AttributeError, KeyError, TypeError): |
| 59 | next_module_line = None |
| 60 | end = (next_module_line - 1) if next_module_line else len(lines) |
| 61 | |
| 62 | spans.append((start, end)) |
| 63 | return spans |
| 64 | |
| 65 | |
| 66 | def range_intersects_spans(start, length, spans): |
| 67 | if length == 0: |
| 68 | changed_start = start |
| 69 | changed_end = start |
| 70 | else: |
| 71 | changed_start = start |
| 72 | changed_end = start + length - 1 |
| 73 | return any(changed_start <= span_end and changed_end >= span_start for span_start, span_end in spans) |
| 74 | |
| 75 | |
| 76 | def metadata_metrics_touched(diff_range, path): |
| 77 | if not path.exists(): |
| 78 | return True |
| 79 | |
| 80 | diff = run_git('diff', '--unified=0', diff_range, '--', relpath(path)) |
| 81 | if not diff.strip(): |
| 82 | return False |
| 83 | |
| 84 | spans = metadata_metrics_spans(path) |
| 85 | if not spans: |
| 86 | return True |
| 87 | |
| 88 | for line in diff.splitlines(): |
| 89 | match = HUNK_RE.match(line) |
| 90 | if not match: |
| 91 | continue |
| 92 | start = int(match.group(1)) |
| 93 | length = int(match.group(2) or '1') |
| 94 | if range_intersects_spans(start, length, spans): |
| 95 | return True |
| 96 | return False |
| 97 | |
| 98 | |
| 99 | def touched_collectors(diff_range): |
| 100 | output = run_git('diff', '--name-status', diff_range) |
| 101 | touched = set() |
| 102 | for line in output.splitlines(): |
| 103 | if not line.strip(): |
| 104 | continue |
| 105 | fields = line.split('\t') |
| 106 | status = fields[0] |
| 107 | path = REPO_PATH / fields[-1] |
| 108 | name = path.name |
| 109 | |
| 110 | if name == 'taxonomy.yaml': |
| 111 | touched.add(path.parent) |
| 112 | elif name == 'metadata.yaml': |
| 113 | if status.startswith(('A', 'D')): |
| 114 | touched.add(path.parent) |
| 115 | elif metadata_metrics_touched(diff_range, path): |
| 116 | touched.add(path.parent) |
| 117 | return sorted(touched) |
| 118 | |
| 119 | |
| 120 | def check_touched_coverage(diff_range): |
| 121 | findings = [] |
| 122 | for collector_dir in touched_collectors(diff_range): |
| 123 | taxonomy_path = collector_dir / 'taxonomy.yaml' |
| 124 | metadata_path = collector_dir / 'metadata.yaml' |
| 125 | if not taxonomy_path.exists() and not metadata_path.exists(): |
| 126 | continue |
| 127 | if not taxonomy_path.exists(): |
| 128 | findings.append(Finding( |
| 129 | code='TAX030', |
| 130 | severity=FATAL, |
| 131 | path=taxonomy_path, |
| 132 | message='Collector metrics or taxonomy changed, but taxonomy.yaml is missing.', |
| 133 | )) |
| 134 | return findings |
| 135 | |
| 136 | |
| 137 | def main(): |
| 138 | parser = argparse.ArgumentParser(description='Validate collector taxonomy coverage and taxonomy artifact generation.') |
| 139 | parser.add_argument('--pr-diff', help='Git diff range for touched-collector coverage, for example origin/master...HEAD.') |
| 140 | args = parser.parse_args() |
| 141 | |
| 142 | findings = [] |
| 143 | if args.pr_diff: |
| 144 | findings.extend(check_touched_coverage(args.pr_diff)) |
| 145 | |
| 146 | _, taxonomy_findings = build_taxonomy() |
| 147 | findings.extend(taxonomy_findings) |
| 148 | |
| 149 | for finding in findings: |
| 150 | print(finding.render(), file=sys.stderr) |
| 151 | |
| 152 | return 1 if any(finding.severity == FATAL for finding in findings) else 0 |
| 153 | |
| 154 | |
| 155 | if __name__ == '__main__': |
| 156 | sys.exit(main()) |