feat: 增加修订对比;

demo/spire_doc_revision_compare_demo.py

-from spire.doc import *
+import argparse
 import difflib
+from itertools import zip_longest
+from pathlib import Path
 
+from openpyxl import Workbook
+from openpyxl.styles import Alignment, Font
 
-# 将文本写入文件
-def WriteAllText(fname: str, text: str):
-    with open(fname, "w", encoding="utf-8") as fp:
-        fp.write(text)
 
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Compare Word revision text and write diff rows to Excel.")
+    parser.add_argument("--input_file", default=r'D:\VsProject\lufa-contract\demo\5、[修订后复审版]麓谷发展集团2026-2027年质量.docx',
+                        help="Path to the Word document with revisions.")
+    parser.add_argument(
+        "-o",
+        "--output",
+        help="Path to the output Excel file. Defaults to '<input_stem>_修订对比.xlsx'.",
+    )
+    parser.add_argument(
+        "--show-text",
+        action="store_true",
+        help="Print full text before and after accepting revisions.",
+    )
+    parser.add_argument(
+        "--no-diff-print",
+        action="store_true",
+        help="Do not print unified diff to the console.",
+    )
+    return parser.parse_args()
+
+
+def get_default_output_file(input_file: Path) -> Path:
+    return input_file.with_name(f"{input_file.stem}_修订对比.xlsx")
+
+
+def read_revision_texts(input_file: Path) -> tuple[str, str]:
+    from spire.doc import Document
+
+    doc = Document()
+    try:
+        doc.LoadFromFile(str(input_file))
+        before_text = doc.GetText()
+
+        if doc.HasChanges:
+            doc.AcceptChanges()
+
+        after_text = doc.GetText()
+        return before_text, after_text
+    finally:
+        doc.Close()
+
+
+def build_unified_diff(before_lines: list[str], after_lines: list[str]) -> list[str]:
+    return list(
+        difflib.unified_diff(
+            before_lines,
+            after_lines,
+            fromfile="before_revision",
+            tofile="after_revision",
+            lineterm="",
+        )
+    )
+
+
+def build_diff_rows(before_lines: list[str], after_lines: list[str]) -> list[tuple[str, str]]:
+    rows: list[tuple[str, str]] = []
+    matcher = difflib.SequenceMatcher(None, before_lines, after_lines)
+
+    for tag, before_start, before_end, after_start, after_end in matcher.get_opcodes():
+        if tag == "equal":
+            continue
+
+        before_part = before_lines[before_start:before_end]
+        after_part = after_lines[after_start:after_end]
+
+        if tag == "replace":
+            rows.extend(
+                (before_line or "", after_line or "")
+                for before_line, after_line in zip_longest(before_part, after_part)
+            )
+        elif tag == "delete":
+            rows.extend((before_line, "") for before_line in before_part)
+        elif tag == "insert":
+            rows.extend(("", after_line) for after_line in after_part)
+
+    return rows
+
+
+def write_diff_rows_to_excel(diff_rows: list[tuple[str, str]], output_file: Path) -> None:
+    wb = Workbook()
+    ws = wb.active
+    ws.title = "revision_compare"
+    ws.append(["修订前", "修订后"])
+
+    for cell in ws[1]:
+        cell.font = Font(bold=True)
+        cell.alignment = Alignment(horizontal="center", vertical="center")
+
+    for before_line, after_line in diff_rows:
+        ws.append([before_line, after_line])
+
+    for row in ws.iter_rows(min_row=2):
+        for cell in row:
+            cell.alignment = Alignment(wrap_text=True, vertical="top")
+        if row[1].value:
+            row[1].font = Font(color="FF0000")
+
+    ws.column_dimensions["A"].width = 80
+    ws.column_dimensions["B"].width = 80
+    ws.freeze_panes = "A2"
+    wb.save(output_file)
+
+
+def compare_revisions(input_file: Path, output_file: Path, show_text: bool, print_diff: bool) -> bool:
+    before_text, after_text = read_revision_texts(input_file)
+
+    if show_text:
+        print("===== 修订前文本 =====")
+        print(before_text)
+        print("===== 修订后文本 =====")
+        print(after_text)
 
-inputFile = "/home/ccran/lufa-contract/demo/修订测试.docx"
+    if before_text == after_text:
+        print("修订前后文本一致，无差异，不写入 Excel。")
+        return False
 
-# 创建Document类的对象
-doc = Document()
+    before_lines = before_text.splitlines()
+    after_lines = after_text.splitlines()
+    diff_lines = build_unified_diff(before_lines, after_lines)
+    diff_rows = build_diff_rows(before_lines, after_lines)
 
-# 加载Word文档
-doc.LoadFromFile(inputFile)
-before_text = doc.GetText()
-print("===== 修订前文本 =====")
-print(before_text)
+    if not diff_rows:
+        print("没有检测到真实差异，不写入 Excel。")
+        return False
 
-# 检查文档是否有未接受的修订
-if doc.HasChanges:
-    # 接受所有修订
-    doc.AcceptChanges()
+    if print_diff:
+        print("===== Diff 对比结果 =====")
+        print("\n".join(diff_lines))
 
-after_text = doc.GetText()
-print("===== 修订后文本 =====")
-print(after_text)
+    write_diff_rows_to_excel(diff_rows, output_file)
+    print(f"Excel Diff 对比结果已写入: {output_file}")
+    return True
 
-before_lines = before_text.splitlines()
-after_lines = after_text.splitlines()
 
-diff_lines = list(
-    difflib.unified_diff(
-        before_lines,
-        after_lines,
-        fromfile="before_revision",
-        tofile="after_revision",
-        lineterm="",
+def main() -> None:
+    args = parse_args()
+    input_file = Path(args.input_file)
+    output_file = Path(args.output) if args.output else get_default_output_file(input_file)
+    compare_revisions(
+        input_file=input_file,
+        output_file=output_file,
+        show_text=args.show_text,
+        print_diff=not args.no_diff_print,
     )
-)
 
-print("===== Diff 对比结果 =====")
-if diff_lines:
-    print("\n".join(diff_lines))
-else:
-    print("修订前后文本一致，无差异。")
 
-doc.Close()
+if __name__ == "__main__":
+    main()