mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
efd2ac1ca4
`.gitattributes` declares `*.py text eol=lf` and `*.sh text eol=lf`, but 74 files (73 .py, 1 .sh) are stored in the index with CRLF line endings, violating that contract. Every macOS/Linux clone reports these files as "modified" on fresh checkout because git's diff engine sees the stored bytes don't match the attribute contract, even though the working tree and index match byte-for-byte. Running `git add --renormalize .` rewrites each affected blob so the stored form matches the attribute declaration. No semantic changes — every affected file's diff is "N insertions, N deletions" with inserts and deletes being the same lines modulo line endings. Follow-up commit adds `.git-blame-ignore-revs` so `git blame` / GitHub blame skip this mechanical commit. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
202 lines
7.2 KiB
Python
202 lines
7.2 KiB
Python
from __future__ import annotations
|
|
|
|
from headroom.transforms.content_detector import (
|
|
ContentType,
|
|
_try_detect_code,
|
|
_try_detect_diff,
|
|
_try_detect_html,
|
|
_try_detect_json,
|
|
_try_detect_log,
|
|
_try_detect_search,
|
|
detect_content_type,
|
|
is_json_array_of_dicts,
|
|
)
|
|
from headroom.transforms.error_detection import (
|
|
ERROR_INDICATOR_KEYWORDS,
|
|
ERROR_KEYWORDS,
|
|
ERROR_PATTERN,
|
|
IMPORTANCE_KEYWORDS,
|
|
IMPORTANCE_PATTERN,
|
|
PRIORITY_PATTERNS_DIFF,
|
|
PRIORITY_PATTERNS_SEARCH,
|
|
PRIORITY_PATTERNS_TEXT,
|
|
SECURITY_KEYWORDS,
|
|
SECURITY_PATTERN,
|
|
WARNING_PATTERN,
|
|
content_has_error_indicators,
|
|
)
|
|
|
|
|
|
def test_detect_content_type_handles_empty_and_plain_text() -> None:
|
|
empty = detect_content_type(" ")
|
|
assert empty.content_type is ContentType.PLAIN_TEXT
|
|
assert empty.confidence == 0.0
|
|
|
|
plain = detect_content_type("just a normal paragraph with no strong patterns")
|
|
assert plain.content_type is ContentType.PLAIN_TEXT
|
|
assert plain.confidence == 0.5
|
|
|
|
|
|
def test_json_detection_distinguishes_dict_arrays_and_other_lists() -> None:
|
|
dict_result = _try_detect_json('[{"id": 1}, {"id": 2}]')
|
|
assert dict_result is not None
|
|
assert dict_result.content_type is ContentType.JSON_ARRAY
|
|
assert dict_result.confidence == 1.0
|
|
assert dict_result.metadata == {"item_count": 2, "is_dict_array": True}
|
|
|
|
scalar_result = _try_detect_json("[1, 2, 3]")
|
|
assert scalar_result is not None
|
|
assert scalar_result.confidence == 0.8
|
|
assert scalar_result.metadata == {"item_count": 3, "is_dict_array": False}
|
|
|
|
empty_result = _try_detect_json("[]")
|
|
assert empty_result is not None
|
|
assert empty_result.metadata == {"item_count": 0, "is_dict_array": False}
|
|
|
|
assert _try_detect_json('{"id": 1}') is None
|
|
assert _try_detect_json("[not valid json") is None
|
|
assert is_json_array_of_dicts('[{"id": 1}]') is True
|
|
assert is_json_array_of_dicts('["value"]') is False
|
|
|
|
|
|
def test_diff_detection_tracks_headers_and_changes() -> None:
|
|
diff = "\n".join(
|
|
[
|
|
"diff --git a/app.py b/app.py",
|
|
"--- a/app.py",
|
|
"@@ -1,2 +1,2 @@",
|
|
"-old line",
|
|
"+new line",
|
|
]
|
|
)
|
|
result = _try_detect_diff(diff)
|
|
assert result is not None
|
|
assert result.content_type is ContentType.GIT_DIFF
|
|
assert result.metadata["header_matches"] == 3
|
|
assert result.metadata["change_lines"] == 2
|
|
assert result.confidence == 1.0
|
|
assert detect_content_type(diff).content_type is ContentType.GIT_DIFF
|
|
|
|
assert _try_detect_diff("+not enough by itself") is None
|
|
|
|
|
|
def test_html_detection_requires_real_structure() -> None:
|
|
html = """
|
|
<!DOCTYPE html>
|
|
<html>
|
|
<head><meta charset="utf-8"></head>
|
|
<body><main><section><div>Hello</div><nav>Links</nav></section></main></body>
|
|
</html>
|
|
"""
|
|
result = _try_detect_html(html)
|
|
assert result is not None
|
|
assert result.content_type is ContentType.HTML
|
|
assert result.metadata["has_doctype"] is True
|
|
assert result.metadata["has_html_tag"] is True
|
|
assert result.metadata["structural_tags"] >= 3
|
|
assert detect_content_type(html).content_type is ContentType.HTML
|
|
|
|
assert _try_detect_html("<div>only one tag</div>") is None
|
|
assert _try_detect_html("<html><title>too sparse</title></html>") is None
|
|
|
|
|
|
def test_search_detection_uses_match_ratio() -> None:
|
|
search_output = "\n".join(
|
|
[
|
|
"src/app.py:10:def main():",
|
|
"src/app.py:20:print('hello')",
|
|
"README.md:5:usage docs",
|
|
"plain text footer",
|
|
]
|
|
)
|
|
result = _try_detect_search(search_output)
|
|
assert result is not None
|
|
assert result.content_type is ContentType.SEARCH_RESULTS
|
|
assert result.metadata == {"matching_lines": 3, "total_lines": 4}
|
|
assert result.confidence == 0.85
|
|
assert detect_content_type(search_output).content_type is ContentType.SEARCH_RESULTS
|
|
|
|
assert _try_detect_search("one:1:match\nplain\nplain\nplain") is None
|
|
assert _try_detect_search("\n\n") is None
|
|
|
|
|
|
def test_log_detection_prefers_build_output_patterns() -> None:
|
|
log_output = "\n".join(
|
|
[
|
|
"2025-01-01 Starting run",
|
|
"ERROR failed to compile",
|
|
"WARNING retrying build",
|
|
"PASSED unit test",
|
|
"Traceback (most recent call last)",
|
|
"plain footer",
|
|
]
|
|
)
|
|
result = _try_detect_log(log_output)
|
|
assert result is not None
|
|
assert result.content_type is ContentType.BUILD_OUTPUT
|
|
assert result.metadata == {"pattern_matches": 5, "error_matches": 2, "total_lines": 6}
|
|
assert result.confidence == 0.8166666666666667
|
|
assert detect_content_type(log_output).content_type is ContentType.BUILD_OUTPUT
|
|
|
|
assert _try_detect_log("plain\ntext\nonly") is None
|
|
assert _try_detect_log("\n\n") is None
|
|
assert _try_detect_log("\n".join(["ERROR one", *["plain"] * 15])) is None
|
|
|
|
|
|
def test_code_detection_identifies_language_and_thresholds() -> None:
|
|
python_code = "\n".join(
|
|
[
|
|
"import os",
|
|
"from pathlib import Path",
|
|
"",
|
|
"@cached",
|
|
"class App:",
|
|
" pass",
|
|
"def main():",
|
|
' """Run."""',
|
|
]
|
|
)
|
|
result = _try_detect_code(python_code)
|
|
assert result is not None
|
|
assert result.content_type is ContentType.SOURCE_CODE
|
|
assert result.metadata == {"language": "python", "pattern_matches": 6}
|
|
assert result.confidence == 0.8628571428571429
|
|
assert detect_content_type(python_code).content_type is ContentType.SOURCE_CODE
|
|
|
|
assert _try_detect_code("function maybe() {}\nplain text") is None
|
|
assert _try_detect_code("import os\ndef main():") is None
|
|
assert _try_detect_code("\n\n") is None
|
|
|
|
|
|
def test_detect_content_type_respects_priority_order() -> None:
|
|
diff_like_search = "\n".join(
|
|
[
|
|
"diff --git a/src/app.py b/src/app.py",
|
|
"@@ -1,1 +1,1 @@",
|
|
"+src/app.py:10:def still_diff_first()",
|
|
]
|
|
)
|
|
assert detect_content_type(diff_like_search).content_type is ContentType.GIT_DIFF
|
|
|
|
|
|
def test_error_detection_keywords_patterns_and_indicator_helper() -> None:
|
|
assert {"error", "failed", "critical"} <= ERROR_KEYWORDS
|
|
assert {"warning", "todo", "fix"} <= IMPORTANCE_KEYWORDS
|
|
assert {"security", "password", "token"} <= SECURITY_KEYWORDS
|
|
assert ERROR_INDICATOR_KEYWORDS[0] == "error"
|
|
|
|
assert ERROR_PATTERN.search("Fatal error occurred")
|
|
assert WARNING_PATTERN.search("warning: be careful")
|
|
assert IMPORTANCE_PATTERN.search("TODO fix this hack")
|
|
assert SECURITY_PATTERN.search("rotate the auth token")
|
|
|
|
assert PRIORITY_PATTERNS_SEARCH[:3] == [ERROR_PATTERN, WARNING_PATTERN, IMPORTANCE_PATTERN]
|
|
assert PRIORITY_PATTERNS_DIFF == [ERROR_PATTERN, IMPORTANCE_PATTERN, SECURITY_PATTERN]
|
|
assert PRIORITY_PATTERNS_TEXT[0] is ERROR_PATTERN
|
|
assert PRIORITY_PATTERNS_TEXT[1] is IMPORTANCE_PATTERN
|
|
assert PRIORITY_PATTERNS_TEXT[2].match("## Header")
|
|
assert PRIORITY_PATTERNS_TEXT[3].match("**Bold")
|
|
assert PRIORITY_PATTERNS_TEXT[4].match("> quote")
|
|
|
|
assert content_has_error_indicators("TRACEBACK: Fatal crash in worker") is True
|
|
assert content_has_error_indicators("Everything completed successfully") is False
|