Add architecture documentation and retail system workshop PPT

Architecture-Diagram/extract_component_data_to_md.py

@@ -0,0 +1,101 @@
+# pyright: reportMissingImports=false
+
+from __future__ import annotations
+
+from pathlib import Path
+import re
+
+from openpyxl import load_workbook
+
+
+ROOT = Path(__file__).resolve().parent
+SOURCE_FILE = ROOT.parent / "202606 Conti Retail APP Component data source.xlsx"
+OUTPUT_FILE = ROOT / f"{SOURCE_FILE.stem}.md"
+
+FIELDS = [
+    ("编号", 2),
+    ("模块", 3),
+    ("功能", 4),
+    ("负责人", 5),
+    ("前置任务", 6),
+    ("数据集", 7),
+    ("来源", 8),
+    ("安全", 9),
+    ("备注", 10),
+]
+
+
+def normalize_cell(value: object) -> str:
+    if value is None:
+        return ""
+
+    if isinstance(value, float) and value.is_integer():
+        value = int(value)
+
+    text = str(value).replace("\r\n", "\n").replace("\r", "\n")
+    lines = [re.sub(r"\s+", " ", line).strip() for line in text.split("\n")]
+    return "\n".join(line for line in lines if line)
+
+
+def add_field(parts: list[str], name: str, value: str) -> None:
+    if not value:
+        return
+
+    parts.append(f"**{name}**")
+    parts.append("")
+
+    lines = [line.strip() for line in value.splitlines() if line.strip()]
+    if len(lines) > 1:
+        parts.extend(f"- {line}" for line in lines)
+    else:
+        parts.extend(lines)
+
+    parts.append("")
+
+
+def extract_workbook_to_md() -> None:
+    workbook = load_workbook(SOURCE_FILE, data_only=True)
+    parts: list[str] = [f"# {SOURCE_FILE.stem}", ""]
+
+    for worksheet in workbook.worksheets:
+        rows: list[dict[str, str]] = []
+
+        for row_index in range(2, worksheet.max_row + 1):
+            row = {
+                field: normalize_cell(worksheet.cell(row=row_index, column=column).value)
+                for field, column in FIELDS
+            }
+            if not any(row.values()):
+                continue
+            if not any(row[key] for key in ("编号", "模块", "功能")):
+                continue
+            rows.append(row)
+
+        if not rows:
+            continue
+
+        parts.append(f"## {worksheet.title}")
+        parts.append("")
+
+        for row in rows:
+            number = row["编号"]
+            module = row["模块"]
+            title = " ".join(part for part in (number, module) if part).strip()
+            level = min(6, 3 + number.count(".")) if number else 3
+
+            parts.append(f"{'#' * level} {title or 'Untitled'}")
+            parts.append("")
+            add_field(parts, "功能", row["功能"])
+            add_field(parts, "负责人", row["负责人"])
+            add_field(parts, "前置任务", row["前置任务"])
+            add_field(parts, "数据集", row["数据集"])
+            add_field(parts, "来源", row["来源"])
+            add_field(parts, "安全", row["安全"])
+            add_field(parts, "备注", row["备注"])
+
+    OUTPUT_FILE.write_text("\n".join(parts).strip() + "\n", encoding="utf-8")
+    print("Wrote workbook markdown output")
+
+
+if __name__ == "__main__":
+    extract_workbook_to_md()