perf: avoid repeated line feature work in Flash PDF

mineru/model/flash/pdf/line_merging.py

@@ -63,8 +63,14 @@ def union(left_index: int, right_index: int) -> None:
         if left_root != right_root:
             parents[right_root] = left_root
 
+    # 只枚举满足必要分类条件的行对，组内仍按原索引递增，保持并查集认领顺序。
+    compatible_indices: dict[tuple[int, bool, str | None], list[int]] = {}
+    for index, line in enumerate(lines):
+        compatible_indices.setdefault((line.angle, line.formula_candidate_only, line.semantic_type), []).append(index)
     for left_index, left_line in enumerate(lines):
-        for right_index in range(left_index + 1, len(lines)):
+        for right_index in compatible_indices[(left_line.angle, left_line.formula_candidate_only, left_line.semantic_type)]:
+            if right_index <= left_index:
+                continue
             right_line = lines[right_index]
             if _can_merge_same_baseline_pair(
                 left_line,
@@ -531,8 +537,6 @@ def _can_merge_same_baseline_pair(
         return False
     if first.visual_row_id == second.visual_row_id and (first.split_from_row or second.split_from_row):
         return False
-    if _connection_crosses_table(first.bbox, second.bbox, table_bboxes):
-        return False
     first_height = _line_effective_height(first, first_bbox)
     second_height = _line_effective_height(second, second_bbox)
     has_compatible_dominant_font = not (
@@ -548,13 +552,13 @@ def _can_merge_same_baseline_pair(
         second_bbox,
         second_height,
     ):
-        return True
+        return not _connection_crosses_table(first.bbox, second.bbox, table_bboxes)
     return _touching_same_baseline_geometry(
         first_bbox,
         first_height,
         second_bbox,
         second_height,
-    )
+    ) and not _connection_crosses_table(first.bbox, second.bbox, table_bboxes)
 
 
 def _touching_same_baseline_geometry(

mineru/model/flash/pdf/native_text.py

@@ -811,23 +811,28 @@ def _merge_native_inline_scripts(
 
     candidates: list[tuple[float, int, int, Literal["prefix", "suffix"]]] = []
     detached_candidate_pairs: set[tuple[int, int, Literal["prefix", "suffix"]]] = set()
+    # 候选生成期间行不会修改，按本轮索引缓存字符统计，避免每对行重算字号中位数。
+    compact_texts = ["".join(char for char in line.text if not char.isspace()) for line in lines]
+    reference_markers = [_INLINE_REFERENCE_MARKER_RE.fullmatch(text) is not None for text in compact_texts]
+    local_bboxes = [_rotate_bbox_to_upright(line.bbox, page_size, line.angle) for line in lines]
+    canonical_scales = [_native_typographic_scale(line) for line in lines]
     for small_index, small in enumerate(lines):
-        compact_text = "".join(char for char in small.text if not char.isspace())
+        compact_text = compact_texts[small_index]
         if not compact_text:
             continue
-        small_local_bbox = _rotate_bbox_to_upright(small.bbox, page_size, small.angle)
+        small_local_bbox = local_bboxes[small_index]
         for base_index, base in enumerate(lines):
             if small_index == base_index or small.angle != base.angle or small.visual_row_id == base.visual_row_id:
                 continue
             if small.effective_height <= 0 or base.effective_height <= 0:
                 continue
-            canonical_small_scale = _native_typographic_scale(small)
-            canonical_base_scale = _native_typographic_scale(base)
+            canonical_small_scale = canonical_scales[small_index]
+            canonical_base_scale = canonical_scales[base_index]
             legacy_small_scale = max(0.1, small.effective_height)
             legacy_base_scale = max(0.1, base.effective_height)
             legacy_ratio = legacy_small_scale / legacy_base_scale
             use_canonical_reference_scale = (
-                _INLINE_REFERENCE_MARKER_RE.fullmatch(compact_text) is not None
+                reference_markers[small_index]
                 and not 0.35 <= legacy_ratio <= 0.8
                 and 0.35 <= canonical_small_scale / canonical_base_scale <= 0.8
             )
@@ -838,7 +843,7 @@ def _merge_native_inline_scripts(
                 continue
             if len(compact_text) > 8 and small_local_bbox[2] - small_local_bbox[0] > 3.0 * base_scale:
                 continue
-            base_local_bbox = _rotate_bbox_to_upright(base.bbox, page_size, base.angle)
+            base_local_bbox = local_bboxes[base_index]
             vertical_overlap = max(
                 0.0,
                 min(small_local_bbox[3], base_local_bbox[3]) - max(small_local_bbox[1], base_local_bbox[1]),

mineru/model/flash/pdf/text_styles.py

@@ -1610,14 +1610,14 @@ def _script_line_char_roles(
         local_origins,
         memberships,
     )
-    strong_structural_roles = _strong_structural_script_roles(
-        local_chars,
-        local_tight_bboxes,
-        local_origins,
-    )
     if bool(getattr(line, "compact_formula_cluster", False)) or (
         bool(getattr(line, "restored_inline_cluster", False)) and bool(regions)
     ):
+        strong_structural_roles = _strong_structural_script_roles(
+            local_chars,
+            local_tight_bboxes,
+            local_origins,
+        )
         roles = [strong_structural_roles.get(index, "body") for index in range(len(roles))]
     for index, char in enumerate(chars):
         char_idx = char.get("char_idx")

tests/unittest/test_flash_pdf_native_text.py

@@ -48,6 +48,40 @@ def _line(
     }
 
 
+def test_inline_script_scale_cache_is_linear_and_local_to_each_pass(monkeypatch: pytest.MonkeyPatch) -> None:
+    """每轮字号计算随行数线性增长，后续轮次重新读取已变化的字符字号。"""
+
+    lines = [
+        models._LineItem(
+            text="body",
+            bbox=(10.0, index * 30.0, 30.0, index * 30.0 + 10.0),
+            angle=0,
+            source_index=index,
+            visual_row_id=index,
+            effective_height=10.0,
+            chars=[{"char": "a", "font": {"size": 10.0}}],
+        )
+        for index in range(20)
+    ]
+    observed: list[float] = []
+    original = native_text._native_typographic_scale
+
+    def record_scale(line: models._LineItem) -> float:
+        """记录真实字号计算，验证缓存不跨越行变更边界。"""
+
+        value = original(line)
+        observed.append(value)
+        return value
+
+    monkeypatch.setattr(native_text, "_native_typographic_scale", record_scale)
+    native_text._merge_native_inline_scripts(lines, (100.0, 700.0))
+    assert observed == [10.0] * 20
+    lines[0].chars[0]["font"]["size"] = 12.0
+    observed.clear()
+    native_text._merge_native_inline_scripts(lines, (100.0, 700.0))
+    assert observed == [12.0, *([10.0] * 19)]
+
+
 def test_private_use_decorative_rule_becomes_axis_line() -> None:
     """验证页首宽幅私用区重复字形不再进入文本输出。"""