Update app.py

app.py

@@ -1,6 +1,5 @@
-# verify_bug2.py
+# verify_bug2.py ver2
 # 実行方法: python verify_bug2.py
-# 前提: app.py と同じディレクトリに配置して実行
 
 import re
 import difflib
@@ -144,12 +143,6 @@ def build_active_text_and_map(original, flags):
     index_map = [i for i, _ in active_chars]
     return active_text, index_map
 
-def build_removed_text_and_map(original, flags):
-    removed_chars = [(i, ch) for i, ch in enumerate(original) if not flags[i]]
-    removed_text = ''.join(ch for _, ch in removed_chars)
-    index_map = [i for i, _ in removed_chars]
-    return removed_text, index_map
-
 def tokenize(text):
     pattern = re.compile(
         r'[a-zA-ZａｂｃｄｅｆｇｈｉｊｋｌｍｎｏｐｑｒｓｔｕｖｗｘｙｚＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺ]+|'
@@ -195,7 +188,7 @@ def compare_texts(src, dst, settings):
 
     if src_active != '' or dst_active != '':
         # ---- トークン単位で比較 ----
-        src_tokens = tokenize(src_active)  # [(token_str, pos_in_active), ...]
+        src_tokens = tokenize(src_active)
         dst_tokens = tokenize(dst_active)
 
         src_token_strs = [t[0] for t in src_tokens]
@@ -204,32 +197,21 @@ def compare_texts(src, dst, settings):
         matcher = difflib.SequenceMatcher(None, src_token_strs, dst_token_strs, autojunk=False)
         for tag, i1, i2, j1, j2 in matcher.get_opcodes():
             if tag in ('replace', 'delete') and i2 > i1:
-                # src_tokens[i1..i2-1] の元テキスト位置を求める
-                start_in_active = src_tokens[i1][1]
-                end_in_active   = src_tokens[i2-1][1] + len(src_tokens[i2-1][0])
-                orig_start = src_map[start_in_active]
-                orig_end   = src_map[end_in_active - 1] + 1
+                # active_text内の開始・終了位置
+                a_start = src_tokens[i1][1]
+                a_end   = src_tokens[i2-1][1] + len(src_tokens[i2-1][0])
+                # src_map で元テキスト位置に変換
+                orig_start = src_map[a_start]
+                orig_end   = src_map[a_end - 1] + 1
                 src_diff_ranges.append((orig_start, orig_end))
             if tag in ('replace', 'insert') and j2 > j1:
-                start_in_active = dst_tokens[j1][1]
-                end_in_active   = dst_tokens[j2-1][1] + len(dst_tokens[j2-1][0])
-                orig_start = dst_map[start_in_active]
-                orig_end   = dst_map[end_in_active - 1] + 1
+                a_start = dst_tokens[j1][1]
+                a_end   = dst_tokens[j2-1][1] + len(dst_tokens[j2-1][0])
+                orig_start = dst_map[a_start]
+                orig_end   = dst_map[a_end - 1] + 1
                 dst_diff_ranges.append((orig_start, orig_end))
 
-    # 除去文字の比較
-    src_removed, src_removed_map = build_removed_text_and_map(src, src_flags)
-    dst_removed, dst_removed_map = build_removed_text_and_map(dst, dst_flags)
-
-    if src_removed != dst_removed and (src_active != '' or dst_active != ''):
-        rm_matcher = difflib.SequenceMatcher(None, src_removed, dst_removed, autojunk=False)
-        for tag, i1, i2, j1, j2 in rm_matcher.get_opcodes():
-            if tag in ('replace', 'delete') and i2 > i1:
-                for k in range(i1, i2):
-                    src_diff_ranges.append((src_removed_map[k], src_removed_map[k] + 1))
-            if tag in ('replace', 'insert') and j2 > j1:
-                for k in range(j1, j2):
-                    dst_diff_ranges.append((dst_removed_map[k], dst_removed_map[k] + 1))
+    # ※除去文字の比較は行わない（無視設定した文字はハイライト対象外）
 
     has_diff = bool(src_diff_ranges or dst_diff_ranges)
 
@@ -261,11 +243,10 @@ def compare_texts(src, dst, settings):
     return src_html, dst_html, has_diff
 
 # ============================================================
-# ハイライト範囲を文字列で返すヘルパー
+# ヘルパー・テスト実行関数
 # ============================================================
 
 def extract_highlighted(text, html_result):
-    """HTMLからハイライトされた文字列リストを抽出"""
     pattern = re.compile(r'<span style="[^"]*">(.+?)</span>', re.DOTALL)
     results = []
     for m in pattern.finditer(html_result):
@@ -275,7 +256,6 @@ def extract_highlighted(text, html_result):
 
 def run_test(name, src, dst, settings, expect_src_hl, expect_dst_hl, expect_has_diff):
     src_html, dst_html, has_diff = compare_texts(src, dst, settings)
-
     src_hl = extract_highlighted(src, src_html)
     dst_hl = extract_highlighted(dst, dst_html)
 
@@ -295,7 +275,7 @@ def run_test(name, src, dst, settings, expect_src_hl, expect_dst_hl, expect_has_
     if not ok_diff:
         print(f"  [has_diff] 期待: {expect_has_diff} / 実際: {has_diff}")
 
-OFF = {}  # 全設定オフ
+OFF = {}
 ALL_ON = {
     'ignore_alpha': True, 'ignore_digit': True, 'ignore_kana': True,
     'ignore_yakumono': True, 'ignore_ligature': True, 'ignore_kangxi': True,
@@ -309,217 +289,93 @@ ALL_ON = {
 # ============================================================
 
 print("=" * 60)
-print("バグ2 検証スクリプト")
+print("バグ2 検証スクリプト ver2")
 print("=" * 60)
 
-# TEST-01 相違なし
-run_test(
-    "TEST-01 相違なし",
-    src="吾輩は猫である。名前はまだない。",
-    dst="吾輩は猫である。名前はまだない。",
-    settings=OFF,
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-02 相違あり基本
-run_test(
-    "TEST-02 相違あり基本",
-    src="吾輩は猫である。",
-    dst="吾輩は犬である。",
-    settings=OFF,
-    expect_src_hl=["猫"],
-    expect_dst_hl=["犬"],
-    expect_has_diff=True,
-)
-
-# TEST-03 比較先に追加
-run_test(
-    "TEST-03 比較先に追加",
-    src="abcdef",
-    dst="abcXYZdef",
-    settings=OFF,
-    expect_src_hl=[],
-    expect_dst_hl=["XYZ"],
-    expect_has_diff=True,
-)
-
-# TEST-04 比較元に削除
-run_test(
-    "TEST-04 比較元に削除",
-    src="abcXYZdef",
-    dst="abcdef",
-    settings=OFF,
-    expect_src_hl=["XYZ"],
-    expect_dst_hl=[],
-    expect_has_diff=True,
-)
-
-# TEST-08 約物全半角無視
-run_test(
-    "TEST-08 約物全半角無視",
-    src="吾輩は、猫である。「名前」は（まだ）ない！",
-    dst="吾輩は猫である名前はまだない",
-    settings={'ignore_yakumono': True},
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-09 約物括弧の中身は残る
-run_test(
-    "TEST-09 約物括弧の中身は残る",
-    src="(abc)テスト",
-    dst="abcテスト",
-    settings={'ignore_yakumono': True},
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-19 ハイフン無視
-run_test(
-    "TEST-19 ハイフン無視",
-    src="abc-def－ghi\u2010jkl\u2011mno\u2013pqr\u2014stu",
-    dst="abcdefghijklmnopqrstu",
-    settings={'ignore_hyphen': True},
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-21 スペース削除
-run_test(
-    "TEST-21 スペース削除",
-    src="abc def　ghi",
-    dst="abcdefghi",
-    settings={'ignore_space': True},
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-21 スペース削除 設定オフ（スペースが差分）
-run_test(
-    "TEST-21 スペース削除 設定オフ",
-    src="abc def　ghi",
-    dst="abcdefghi",
-    settings=OFF,
-    expect_src_hl=[" ", "　"],
-    expect_dst_hl=[],
-    expect_has_diff=True,
-)
-
-# TEST-22 改行削除
-run_test(
-    "TEST-22 改行削除",
-    src="abc\ndef\nghi",
-    dst="abcdefghi",
-    settings={'ignore_newline': True},
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-23 約物と括弧付き文字両方
-run_test(
-    "TEST-23 約物と括弧付き文字両方",
-    src="吾輩は(猫)である。名前は【まだ】ない！",
-    dst="吾輩はである。名前はない！",
-    settings={'ignore_yakumono': True, 'ignore_brackets_with_content': True},
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-25 全設定オフ（バグ2メイン修正対象）
-run_test(
-    "TEST-25 全設定オフ",
-    src="abc(def)123アイウ〔ghi〕fi\u2F00zero-test \nabc",
-    dst="xyz(www)789カキクケコ〔jkl〕fl\u2F01one+test \nxyz",
-    settings=OFF,
-    expect_src_hl=["abc", "def", "123", "アイウ", "ghi", "fi", "\u2F00", "zero"],
-    expect_dst_hl=["xyz", "www", "789", "カキクケコ", "jkl", "fl", "\u2F01", "one", "+"],
-    expect_has_diff=True,
-)
-
-# TEST-25 全設定オン
-run_test(
-    "TEST-25 全設定オン",
-    src="abc(def)123アイウ〔ghi〕fi\u2F00zero-test \nabc",
-    dst="xyz(www)789カキクケコ〔jkl〕fl\u2F01one+test \nxyz",
-    settings=ALL_ON,
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-30 スペースのみ相違 設定オフ
-run_test(
-    "TEST-30 スペースのみ相違 設定オフ",
-    src="abc def",
-    dst="abcdef",
-    settings=OFF,
-    expect_src_hl=[" "],
-    expect_dst_hl=[],
-    expect_has_diff=True,
-)
-
-# TEST-35 比較元削除箇所ハイライト
-run_test(
-    "TEST-35 比較元削除箇所ハイライト",
-    src="abcXYZdef",
-    dst="abcdef",
-    settings=OFF,
-    expect_src_hl=["XYZ"],
-    expect_dst_hl=[],
-    expect_has_diff=True,
-)
-
-# TEST-37 ハイフン全種
-run_test(
-    "TEST-37 ハイフン全種",
-    src="abc-def\uFF0Dghi\u2010jkl\u2011mno\u2013pqr\u2014stu",
-    dst="abcdefghijklmnopqrstu",
-    settings={'ignore_hyphen': True},
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-27 空文字
-run_test(
-    "TEST-27 空文字",
-    src="",
-    dst="",
-    settings=OFF,
-    expect_src_hl=[],
-    expect_dst_hl=[],
-    expect_has_diff=False,
-)
-
-# TEST-28 片方空文字
-run_test(
-    "TEST-28 片方空文字",
-    src="abcdef",
-    dst="",
-    settings=OFF,
-    expect_src_hl=["abcdef"],
-    expect_dst_hl=[],
-    expect_has_diff=True,
-)
-
-# TEST-29 改行のみ相違 設定オフ
-run_test(
-    "TEST-29 改行のみ相違 設定オフ",
-    src="\n\n",
-    dst="\n",
-    settings=OFF,
-    expect_src_hl=["\n"],
-    expect_dst_hl=[],
-    expect_has_diff=True,
-)
+run_test("TEST-01 相違なし",
+    "吾輩は猫である。名前はまだない。",
+    "吾輩は猫である。名前はまだない。",
+    OFF, [], [], False)
+
+run_test("TEST-02 相違あり基本",
+    "吾輩は猫である。",
+    "吾輩は犬である。",
+    OFF, ["猫"], ["犬"], True)
+
+run_test("TEST-03 比較先に追加",
+    "abcdef", "abcXYZdef",
+    OFF, [], ["XYZ"], True)
+
+run_test("TEST-04 比較元に削除",
+    "abcXYZdef", "abcdef",
+    OFF, ["XYZ"], [], True)
+
+run_test("TEST-08 約物全半角無視",
+    "吾輩は、猫である。「名前」は（まだ）ない！",
+    "吾輩は猫である名前はまだない",
+    {'ignore_yakumono': True}, [], [], False)
+
+run_test("TEST-09 約物括弧の中身は残る",
+    "(abc)テスト", "abcテスト",
+    {'ignore_yakumono': True}, [], [], False)
+
+run_test("TEST-19 ハイフン無視",
+    "abc-def\uFF0Dghi\u2010jkl\u2011mno\u2013pqr\u2014stu",
+    "abcdefghijklmnopqrstu",
+    {'ignore_hyphen': True}, [], [], False)
+
+run_test("TEST-21 スペース削除 設定オン",
+    "abc def　ghi", "abcdefghi",
+    {'ignore_space': True}, [], [], False)
+
+run_test("TEST-21 スペース削除 設定オフ",
+    "abc def　ghi", "abcdefghi",
+    OFF, [" ", "　"], [], True)
+
+run_test("TEST-22 改行削除 設定オン",
+    "abc\ndef\nghi", "abcdefghi",
+    {'ignore_newline': True}, [], [], False)
+
+run_test("TEST-23 約物と括弧付き文字両方",
+    "吾輩は(猫)である。名前は【まだ】ない！",
+    "吾輩はである。名前はない！",
+    {'ignore_yakumono': True, 'ignore_brackets_with_content': True},
+    [], [], False)
+
+run_test("TEST-25 全設定オフ",
+    "abc(def)123アイウ〔ghi〕fi\u2F00zero-test \nabc",
+    "xyz(www)789カキクケコ〔jkl〕fl\u2F01one+test \nxyz",
+    OFF,
+    ["abc", "def", "123", "アイウ", "ghi", "fi", "\u2F00", "zero"],
+    ["xyz", "www", "789", "カキクケコ", "jkl", "fl", "\u2F01", "one", "+"],
+    True)
+
+run_test("TEST-25 全設定オン",
+    "abc(def)123アイウ〔ghi〕fi\u2F00zero-test \nabc",
+    "xyz(www)789カキクケコ〔jkl〕fl\u2F01one+test \nxyz",
+    ALL_ON, [], [], False)
+
+run_test("TEST-30 スペースのみ相違 設定オフ",
+    "abc def", "abcdef",
+    OFF, [" "], [], True)
+
+run_test("TEST-35 比較元削除箇所ハイライト",
+    "abcXYZdef", "abcdef",
+    OFF, ["XYZ"], [], True)
+
+run_test("TEST-37 ハイフン全種 設定オン",
+    "abc-def\uFF0Dghi\u2010jkl\u2011mno\u2013pqr\u2014stu",
+    "abcdefghijklmnopqrstu",
+    {'ignore_hyphen': True}, [], [], False)
+
+run_test("TEST-27 空文字",
+    "", "", OFF, [], [], False)
+
+run_test("TEST-28 片方空文字",
+    "abcdef", "", OFF, ["abcdef"], [], True)
+
+run_test("TEST-29 改行のみ相違 設定オフ",
+    "\n\n", "\n", OFF, ["\n"], [], True)
 
 print("=" * 60)
 print("完了")