test: 真实样本 Word 解析集成测试(模板/规则/说明书画属write)

This commit is contained in:
lhl
2026-08-10 15:17:44 +08:00
parent 7f29cc9cf3
commit 16921ecbb4
2 changed files with 65 additions and 1 deletions
+1
View File
@@ -66,3 +66,4 @@
| 2026-08-10 | Agent 实现 | Phase3 Task2 实现:WordTemplateParser 章构成/占位符/样式名提取。新建 src/genesis/parsers/_word_common.pyheading_level 共享 helperTask2/3 复用,从 Heading N 样式名解析大纲级别,非数字/无后缀兜底 1)与 src/genesis/parsers/word_template_parser.pyPLACEHOLDER_RE 统一占位符正则 {{键名}}/{{键名:章节名}}Heading 段落→heading 章标记、bookmarkStart→bookmark、占位符→placeholder 并写 placeholders{名:段落上下文}styles 提取 defined/used 样式名集合去重);tests/test_word_template_parser.py 按 brief 8 用例(6 解析 + 2 heading_level 兜底分支);覆盖补齐:bookmark 用例增加无 name 的 bookmarkStart 覆盖 if name 假分支(98%→100%);TDD 验证 REDModuleNotFoundError: No module named 'genesis.parsers._word_common')→ GREEN(聚焦 8 passed);pytest 全量 140 passed 覆盖 100.00%841 stmts/200 br),fail_under=99 达标 | src/genesis/parsers/_word_common.py, src/genesis/parsers/word_template_parser.py, tests/test_word_template_parser.py, _AI_USAGE_LOG.md | deepseek-v4-flash-free |
| 2026-08-10 | Agent 实现 | Phase3 Task3 实现:RuleDocParser 规则文档 Markdown 化与分类。新建 src/genesis/parsers/rule_doc_parser.pybody 级遍历保段落/表格交错顺序;Heading N→#×N;列表双通道检测 List 样式或 ・/-/• 前缀;表格→GFM;空段→空行;file_type 固定 word、hash=sha256 hex;复用 _word_common.heading_level 无本地重复)与 tests/test_rule_doc_parser.py 按 brief 6 用例;覆盖补齐:test_parse_empty_document 增加 doc.add_paragraph("") 使空段分支(原 new_document 无任何 w:p 不进分支)达 100%TDD 验证 REDModuleNotFoundError: No module named 'genesis.parsers.rule_doc_parser')→ GREEN(聚焦 6 passed);pytest 全量 146 passed 覆盖 100.00%886 stmts/218 br),fail_under=99 达标 | src/genesis/parsers/rule_doc_parser.py, tests/test_rule_doc_parser.py, _AI_USAGE_LOG.md | deepseek-v4-flash-free |
| 2026-08-10 | Agent 实现 | Phase3 Task4 实现:SourceParser 门面全量输入聚合。新建 src/genesis/parsers/source_aggregator.py(角色显式传参无隐式猜测;requirements 校验 .xlsx/.xls 后缀聚合 tables/commentstemplate 校验 .docx 用 WordTemplateParser 解析;write_instruction+rule 校验 .docx 按 category='write' 归入 rule_docs;不存在抛 FileNotFoundError、未知扩展名抛 ValueError('不支持的文件类型: ...')image_analyses=[]/existing_system=None 固定)与 tests/test_source_aggregator.py 按 brief 6 用例 + 补 4 用例(模板未知扩展名、规则路径文件缺失、requirements/规则无扩展名兜底 '无扩展名' 文案,覆盖 51/62 行缺失与 or 表达式分支)达 100%TDD 验证 REDModuleNotFoundError: No module named 'genesis.parsers.source_aggregator')→ GREEN(聚焦 10 passed);pytest 全量 156 passed 覆盖 100.00%929 stmts/236 br),fail_under=99 达标 | src/genesis/parsers/source_aggregator.py, tests/test_source_aggregator.py, _AI_USAGE_LOG.md | deepseek-v4-flash-free |
| 2026-08-10 | 测试验证 | Phase3 Task5 实现:真实样本 Word 解析集成测试。tests/test_real_samples.py 追加 4 用例(保留现有 4 个 Excel 用例与 _x 辅助):模板→7 H1(はじめに…バッチ一覧)+section:introduction/doc_title 占位符+template_start 书签;记入規則→category=write/file_type=word/# 1. 機能一覧の書き方/- 機能ID は F001 から連番で付与する。(・前缀双通道检测);做成説明書→category=write/# 2. 機能一覧;全量组装→tables 非空+template 非空+rule_docs==2 且全 write;聚焦测试 8 passed 无 skippytest 全量 160 passed 覆盖 100.00%929 stmts/236 br),fail_under=99 达标 | tests/test_real_samples.py, _AI_USAGE_LOG.md | deepseek-v4-flash-free |
+64 -1
View File
@@ -3,10 +3,17 @@ from pathlib import Path
import pytest
from genesis.parsers.excel_parser import ExcelParser
from genesis.parsers.word_template_parser import WordTemplateParser
from genesis.parsers.rule_doc_parser import RuleDocParser
from genesis.parsers.source_aggregator import SourceParser
SAMPLES = Path(__file__).resolve().parents[1] / "samples"
def _d(name: str) -> Path:
return SAMPLES / name
def _x(name: str) -> Path:
return SAMPLES / name
@@ -57,4 +64,60 @@ def test_mixed_sample_segments_detected():
# 碎片段含 ・ 与 ■ 两行文本
ft = [p for p in mixed.paragraphs if p.kind == "free_text"][0]
assert "改修ポイント" in (ft.text or "")
assert "対象期間" in (ft.text or "")
assert "対象期間" in (ft.text or "")
def test_word_template_sample_chapters_and_placeholders():
p = _d("概要設計書テンプレート.docx")
if not p.exists():
pytest.skip("样本缺失")
result = WordTemplateParser().parse(p)
headings = [s for s in result.sections if s.type == "heading"]
h1 = [h for h in headings if h.level == 1]
assert len(h1) == 7
assert h1[0].name == "1. はじめに"
assert h1[-1].name == "7. バッチ一覧"
assert "section:introduction" in result.placeholders
assert "doc_title" in result.placeholders
bookmarks = [s for s in result.sections if s.type == "bookmark"]
assert len(bookmarks) == 1
assert bookmarks[0].name == "template_start"
def test_rule_doc_sample_markdown_and_category():
p = _d("記入規則.docx")
if not p.exists():
pytest.skip("样本缺失")
result = RuleDocParser().parse(p, category="write")
assert result.category == "write"
assert result.file_type == "word"
assert "# 1. 機能一覧の書き方" in result.markdown_content
assert "- 機能ID は F001 から連番で付与する。" in result.markdown_content
def test_write_instruction_sample_category_write():
p = _d("概要設計做成説明書.docx")
if not p.exists():
pytest.skip("样本缺失")
result = RuleDocParser().parse(p, category="write")
assert result.category == "write"
assert "# 2. 機能一覧" in result.markdown_content
def test_source_parser_full_sample_assembly():
xlsx = _x("要件定義_新規開発.xlsx")
template = _d("概要設計書テンプレート.docx")
rule = _d("記入規則.docx")
instr = _d("概要設計做成説明書.docx")
if not all(p.exists() for p in [xlsx, template, rule, instr]):
pytest.skip("样本缺失")
result = SourceParser().parse(
requirement_paths=[xlsx],
template_path=template,
write_instruction_paths=[instr],
rule_paths=[rule],
)
assert result.tables
assert result.template is not None
assert len(result.rule_docs) == 2
assert all(r.category == "write" for r in result.rule_docs)