docvortex 0.2.1__py3-none-any.whl

docvortex/analyzers/native/pdf/text_blocks.py

@@ -0,0 +1,82 @@
+"""保留既有入口的 Flash PDF 门面，内部实现按职责显式组织。"""
+
+from .text_assembly.annotations import (
+    _merge_image_caption_text_blocks as _merge_image_caption_text_blocks,
+    _caption_image_group_bboxes as _caption_image_group_bboxes,
+    _caption_seed_matches_image as _caption_seed_matches_image,
+    _caption_body_has_structural_gap as _caption_body_has_structural_gap,
+    _caption_tail_matches_seed as _caption_tail_matches_seed,
+    _merge_multiline_title_blocks as _merge_multiline_title_blocks,
+    _merge_fragmented_header_blocks as _merge_fragmented_header_blocks,
+    _merge_front_matter_column_blocks as _merge_front_matter_column_blocks,
+    _merge_repeated_compact_title_continuations as _merge_repeated_compact_title_continuations,
+)
+from .text_assembly.assembly import _build_text_blocks as _build_text_blocks
+from .text_assembly.common import (
+    _REFERENCE_ENTRY_RE as _REFERENCE_ENTRY_RE,
+    _FIGURE_CAPTION_MARKER_RE as _FIGURE_CAPTION_MARKER_RE,
+    _INLINE_MATH_RECOVERY_MARKER as _INLINE_MATH_RECOVERY_MARKER,
+    _PARAGRAPH_FORMULA_CONTEXT_MARKER as _PARAGRAPH_FORMULA_CONTEXT_MARKER,
+    _FRONT_MATTER_FIELD_RE as _FRONT_MATTER_FIELD_RE,
+    _LIST_ITEM_RE as _LIST_ITEM_RE,
+    _BULLET_ITEM_RE as _BULLET_ITEM_RE,
+    _EMAIL_METADATA_RE as _EMAIL_METADATA_RE,
+    _ABSTRACT_METADATA_RE as _ABSTRACT_METADATA_RE,
+    _LABELLED_METADATA_RE as _LABELLED_METADATA_RE,
+    _URL_LINE_RE as _URL_LINE_RE,
+    _SHORT_SAME_BASELINE_PREFIX_RE as _SHORT_SAME_BASELINE_PREFIX_RE,
+    _merge_internal_text_block_group as _merge_internal_text_block_group,
+    _component_declared_lane_interval as _component_declared_lane_interval,
+    _component_lane_interval as _component_lane_interval,
+    _component_reference_width as _component_reference_width,
+    _compatible_component_lane_width as _compatible_component_lane_width,
+    _components_share_lane_role as _components_share_lane_role,
+    _block_starts_with_short_wide_rows as _block_starts_with_short_wide_rows,
+    _find_short_opener_pairs as _find_short_opener_pairs,
+    _nearest_following_text_component as _nearest_following_text_component,
+    _has_parallel_text_component as _has_parallel_text_component,
+    _nearest_tapered_tail_component as _nearest_tapered_tail_component,
+    _component_connection_skips_block as _component_connection_skips_block,
+    _text_component_sort_key as _text_component_sort_key,
+    _merge_text_line_content as _merge_text_line_content,
+)
+from .text_assembly.footnotes import (
+    _build_grouped_page_footnote_blocks as _build_grouped_page_footnote_blocks,
+    _split_page_footnote_entries as _split_page_footnote_entries,
+    _find_page_footnote_marker_rows as _find_page_footnote_marker_rows,
+    _find_geometric_page_footnote_marker_rows as _find_geometric_page_footnote_marker_rows,
+    _split_marked_page_footnote_entries as _split_marked_page_footnote_entries,
+    _split_unmarked_page_footnote_entries as _split_unmarked_page_footnote_entries,
+    _tight_page_footnote_bboxes as _tight_page_footnote_bboxes,
+)
+from .text_assembly.merging import (
+    _merge_short_same_baseline_prefix_blocks as _merge_short_same_baseline_prefix_blocks,
+    _blocks_share_boundary_visual_row as _blocks_share_boundary_visual_row,
+    _merge_overlapping_same_line_text_blocks as _merge_overlapping_same_line_text_blocks,
+    _merge_inline_math_fragment_text_blocks as _merge_inline_math_fragment_text_blocks,
+    _component_local_union_bbox as _component_local_union_bbox,
+    _merge_paragraph_formula_context_blocks as _merge_paragraph_formula_context_blocks,
+    _merge_residual_narrow_math_text_blocks as _merge_residual_narrow_math_text_blocks,
+    _merge_hostless_inline_math_fragment_blocks as _merge_hostless_inline_math_fragment_blocks,
+    _merge_inline_math_recovery_group as _merge_inline_math_recovery_group,
+    _merge_inline_math_paragraph_continuations as _merge_inline_math_paragraph_continuations,
+    _merge_spatial_text_components as _merge_spatial_text_components,
+    _merge_list_intro_text_components as _merge_list_intro_text_components,
+    _merge_unterminated_text_components as _merge_unterminated_text_components,
+)
+from .text_assembly.rows import (
+    _local_tight_output_line_bboxes as _local_tight_output_line_bboxes,
+    _starts_structural_reference_entry as _starts_structural_reference_entry,
+    _build_hanging_indent_group_map as _build_hanging_indent_group_map,
+    _infer_local_text_lane_map as _infer_local_text_lane_map,
+    _structured_text_break_sources as _structured_text_break_sources,
+    _isolated_indented_paragraph_break_sources as _isolated_indented_paragraph_break_sources,
+    _centered_visual_reset_break_sources as _centered_visual_reset_break_sources,
+    _leading_typography_reset_break_sources as _leading_typography_reset_break_sources,
+    _formula_style_text_row_break_sources as _formula_style_text_row_break_sources,
+    _front_matter_keyword_break_sources as _front_matter_keyword_break_sources,
+    _component_starts_with_emphasized_row as _component_starts_with_emphasized_row,
+    _explicit_text_break_sources as _explicit_text_break_sources,
+)
+
+__all__ = []

docvortex/analyzers/native/pdf/text_styles.py

@@ -0,0 +1,55 @@
+"""保留既有入口的 Flash PDF 门面，内部实现按职责显式组织。"""
+
+from .inline.detection import (
+    detect_pdf_text_link_lines as detect_pdf_text_link_lines,
+    detect_pdf_text_style_lines as detect_pdf_text_style_lines,
+)
+from .inline.matching import (
+    _assign_lines_to_blocks as _assign_lines_to_blocks,
+    _realign_repaired_text_evidence as _realign_repaired_text_evidence,
+    _partition_resplit_text_evidence as _partition_resplit_text_evidence,
+)
+from .inline.materialize import (
+    apply_pdf_text_links as apply_pdf_text_links,
+    apply_pdf_text_scripts as apply_pdf_text_scripts,
+    apply_pdf_text_styles as apply_pdf_text_styles,
+    materialize_pdf_inline_spans as materialize_pdf_inline_spans,
+)
+from .inline.scripts import (
+    detect_pdf_text_script_lines as detect_pdf_text_script_lines,
+    _fraction_member_indices as _fraction_member_indices,
+    _refine_math_script_tokens as _refine_math_script_tokens,
+    _script_line_char_roles as _script_line_char_roles,
+)
+from .inline.types import (
+    PDF_NATIVE_SCRIPT_MARKUP_KEY as PDF_NATIVE_SCRIPT_MARKUP_KEY,
+    PDF_FONT_FORCE_BOLD_FLAG as PDF_FONT_FORCE_BOLD_FLAG,
+    PDF_FONT_ITALIC_FLAG as PDF_FONT_ITALIC_FLAG,
+    PDFTextLinkLine as PDFTextLinkLine,
+    PDFTextLinkRange as PDFTextLinkRange,
+    PDFTextScriptLine as PDFTextScriptLine,
+    PDFTextScriptRange as PDFTextScriptRange,
+    PDFTextStyle as PDFTextStyle,
+    PDFTextStyleLine as PDFTextStyleLine,
+    PDFTextStyleRange as PDFTextStyleRange,
+)
+
+__all__ = [
+    "PDF_NATIVE_SCRIPT_MARKUP_KEY",
+    "PDF_FONT_FORCE_BOLD_FLAG",
+    "PDF_FONT_ITALIC_FLAG",
+    "PDFTextLinkLine",
+    "PDFTextLinkRange",
+    "PDFTextScriptLine",
+    "PDFTextScriptRange",
+    "PDFTextStyle",
+    "PDFTextStyleLine",
+    "PDFTextStyleRange",
+    "apply_pdf_text_links",
+    "apply_pdf_text_scripts",
+    "apply_pdf_text_styles",
+    "detect_pdf_text_link_lines",
+    "detect_pdf_text_script_lines",
+    "detect_pdf_text_style_lines",
+    "materialize_pdf_inline_spans",
+]

docvortex/analyzers/native/pdf/title_analysis/__init__.py

@@ -0,0 +1,3 @@
+"""按职责拆分的 Flash PDF 内部实现。"""
+
+__all__: list[str] = []

docvortex/analyzers/native/pdf/title_analysis/body_profile.py

@@ -0,0 +1,215 @@
+"""统计全文和栏内正文排版基线。"""
+
+from __future__ import annotations
+
+import statistics
+
+from ..geometry import _rotate_bbox_to_upright
+from ..inline.types import PDF_FONT_FORCE_BOLD_FLAG, PDF_FONT_ITALIC_FLAG
+from ..line_layout import _estimate_lane_gap, _font_signatures_share_family, _line_canonical_style_scale, _line_effective_height
+from ..models import _DocumentBodyProfile, _LaneBodyProfile, _LineItem, _PreparedPage, _TextLane
+
+
+def _infer_document_body_profile(
+    prepared_pages: list[_PreparedPage],
+    *,
+    use_canonical_scale: bool = False,
+) -> _DocumentBodyProfile | None:
+    """按跨页覆盖和累计行宽推断全文正文行高及常规字体集合。"""
+
+    samples: list[
+        tuple[
+            float,
+            int,
+            float,
+            tuple[str, int] | None,
+            float | None,
+        ]
+    ] = []
+    for page_index, prepared in enumerate(prepared_pages):
+        for line in prepared.remaining_lines:
+            if line.semantic_type is not None:
+                continue
+            local_bbox = _rotate_bbox_to_upright(
+                line.bbox,
+                prepared.page_size,
+                line.angle,
+            )
+            local_page_width = prepared.page_size[1] if line.angle in {90, 270} else prepared.page_size[0]
+            height = (
+                _line_canonical_style_scale(line, local_bbox)
+                if use_canonical_scale
+                else _line_effective_height(line, local_bbox)
+            )
+            normalized_width = max(0.0, local_bbox[2] - local_bbox[0]) / max(
+                0.1,
+                local_page_width,
+            )
+            if height <= 0 or normalized_width <= 0:
+                continue
+            samples.append(
+                (
+                    height,
+                    page_index,
+                    normalized_width,
+                    line.font_signature if line.font_coverage >= 0.75 else None,
+                    line.dominant_font_weight,
+                )
+            )
+    if not samples:
+        return None
+
+    height_clusters: list[list[tuple[float, int, float]]] = []
+    for height, page_index, normalized_width, _font, _weight in sorted(
+        samples,
+        key=lambda item: item[0],
+    ):
+        target = next(
+            (
+                cluster
+                for cluster in height_clusters
+                if abs(height - statistics.median(item[0] for item in cluster))
+                <= 0.1 * statistics.median(item[0] for item in cluster)
+            ),
+            None,
+        )
+        if target is None:
+            height_clusters.append([(height, page_index, normalized_width)])
+        else:
+            target.append((height, page_index, normalized_width))
+    cross_page_clusters = [cluster for cluster in height_clusters if len({item[1] for item in cluster}) >= 2]
+    eligible_clusters = cross_page_clusters or height_clusters
+    body_cluster = max(
+        eligible_clusters,
+        key=lambda cluster: (
+            sum(item[2] for item in cluster),
+            len({item[1] for item in cluster}),
+            len(cluster),
+        ),
+    )
+    body_height = statistics.median(item[0] for item in body_cluster)
+
+    body_weights = [
+        weight
+        for height, _page_index, _width, _font, weight in samples
+        if weight is not None and 0.9 <= height / body_height <= 1.1
+    ]
+    body_weight = statistics.median(body_weights) if body_weights else None
+
+    font_pages: dict[tuple[str, int], set[int]] = {}
+    font_widths: dict[tuple[str, int], float] = {}
+    font_weights: dict[tuple[str, int], list[float]] = {}
+    for height, page_index, width, font, weight in samples:
+        if font is None or not 0.9 <= height / body_height <= 1.1:
+            continue
+        # 常规字体支持必须来自正文高度带；跨页重复的大标题不能反向污染正文画像。
+        font_pages.setdefault(font, set()).add(page_index)
+        font_widths[font] = font_widths.get(font, 0.0) + width
+        if weight is not None:
+            font_weights.setdefault(font, []).append(weight)
+
+    regular_fonts = frozenset(
+        font
+        for font, pages in font_pages.items()
+        if len(pages) >= 3
+        and font_widths.get(font, 0.0) >= 2.0
+        and font_widths.get(font, 0.0) >= 0.75 * len(pages)
+        and _document_font_is_regular(
+            font,
+            font_weights.get(font, []),
+            body_weight,
+        )
+    )
+    return _DocumentBodyProfile(
+        body_height=max(0.1, body_height),
+        body_weight=body_weight,
+        regular_fonts=regular_fonts,
+        has_style_scale_repairs=any(
+            line.style_scale_repaired for prepared in prepared_pages for line in prepared.remaining_lines
+        ),
+    )
+
+
+def _document_font_is_regular(
+    font: tuple[str, int],
+    weights: list[float],
+    body_weight: float | None,
+) -> bool:
+    """用字体样式位和全文正文基准过滤斜体、粗体等强调字体。"""
+
+    if font[1] & (PDF_FONT_ITALIC_FLAG | PDF_FONT_FORCE_BOLD_FLAG):
+        return False
+    if not weights or body_weight is None:
+        return True
+    median_weight = statistics.median(weights)
+    return median_weight < max(body_weight + 100.0, 1.15 * body_weight)
+
+
+def _infer_lane_body_profile(lane: _TextLane) -> _LaneBodyProfile:
+    """从栏带的长行主体估计正文行高、主字体、字重、常规行距和样式占比。"""
+
+    available = [item for item in lane.lines if item[0].semantic_type is None]
+    if not available:
+        return _LaneBodyProfile(1.0, None, None, 0.35, {})
+    lane_width = max(0.1, lane.right - lane.left)
+    long_lines = [item for item in available if item[1][2] - item[1][0] >= 0.45 * lane_width]
+    body_rows = long_lines or available
+    body_line_ids = {id(line) for line, _bbox in body_rows}
+    body_height = statistics.median(_line_effective_height(line, bbox) for line, bbox in body_rows)
+
+    font_support: dict[tuple[str, int], float] = {}
+    style_support: dict[tuple[str, int], float] = {}
+    total_style_width = 0.0
+    for line, bbox in available:
+        if line.font_signature is None or line.font_coverage < 0.75:
+            continue
+        line_width = max(0.1, bbox[2] - bbox[0])
+        style_support[line.font_signature] = style_support.get(line.font_signature, 0.0) + line_width
+        total_style_width += line_width
+        if id(line) in body_line_ids and 0.75 <= _line_effective_height(line, bbox) / body_height <= 1.35:
+            font_support[line.font_signature] = font_support.get(line.font_signature, 0.0) + line_width
+    body_font = max(font_support, key=font_support.get) if font_support else None
+    if total_style_width > 0:
+        style_support = {signature: width / total_style_width for signature, width in style_support.items()}
+
+    body_weights = [
+        line.dominant_font_weight
+        for line, bbox in body_rows
+        if line.dominant_font_weight is not None
+        and (body_font is None or line.font_signature == body_font)
+        and 0.75 <= _line_effective_height(line, bbox) / body_height <= 1.35
+    ]
+    regular_gap, _gap_mad = _estimate_lane_gap(lane)
+    return _LaneBodyProfile(
+        body_height=max(0.1, body_height),
+        body_font=body_font,
+        body_weight=statistics.median(body_weights) if body_weights else None,
+        regular_gap=regular_gap,
+        style_support=style_support,
+        body_row_count=len(body_rows),
+    )
+
+
+def _line_uses_document_regular_font(
+    line: _LineItem,
+    document_body_profile: _DocumentBodyProfile | None,
+) -> bool:
+    """判断当前行是否使用跨页反复出现且未加粗的常规字体。"""
+
+    return (
+        document_body_profile is not None
+        and line.font_signature is not None
+        and line.font_coverage >= 0.5
+        and any(
+            _font_signatures_share_family(line.font_signature, regular_font)
+            for regular_font in document_body_profile.regular_fonts
+        )
+    )
+
+
+__all__ = [
+    "_infer_document_body_profile",
+    "_document_font_is_regular",
+    "_infer_lane_body_profile",
+    "_line_uses_document_regular_font",
+]

docvortex/analyzers/native/pdf/title_analysis/common.py

@@ -0,0 +1,117 @@
+"""提供标题分类共享的几何与文本规则。"""
+
+from __future__ import annotations
+
+import re
+
+from .....schema import BBox
+from ..geometry import _bbox_axis_overlap_ratio, _bbox_center_x, _bbox_center_y
+from ..line_layout import _effective_text_row_gap
+from ..models import _LineItem
+
+_NUMBERED_SECTION_TITLE_RE = re.compile(
+    r"^(?P<number>\d+(?:\s*\.\s*\d+)*)\s+(?P<label>\S.*)$",
+)
+
+
+_SECTION_NUMBER_ONLY_RE = re.compile(
+    r"^\d+(?:\s*\.\s*\d+)*\.?$",
+)
+
+
+_SECTION_TITLE_TERMINAL_RE = re.compile(
+    r"[.!?。！？:：;；,，]$",
+)
+
+
+_UNNUMBERED_SECTION_HEADING_RE = re.compile(
+    r"^(?:introduction|references?|bibliography|acknowledg(?:e)?ments?|引言|绪论|参考文献|参考资料)$",
+    re.IGNORECASE,
+)
+
+
+def _build_physical_title_gap_map(
+    line_geometry: list[tuple[_LineItem, BBox]],
+) -> dict[int, tuple[float | None, float | None]]:
+    """为每行记录同方向且水平投影相交的最近上、下物理行净空。"""
+
+    output: dict[int, tuple[float | None, float | None]] = {}
+    for line, bbox in line_geometry:
+        line_center = _bbox_center_y(bbox)
+        above_gaps: list[float] = []
+        below_gaps: list[float] = []
+        for other_line, other_bbox in line_geometry:
+            if other_line is line:
+                continue
+            if _bbox_axis_overlap_ratio(bbox, other_bbox, axis="x") < 0.1:
+                # 双栏同高度正文并非当前行的物理上下文，不能抹掉真实标题留白。
+                continue
+            if line.visual_row_id is not None and other_line.visual_row_id == line.visual_row_id:
+                continue
+            other_center = _bbox_center_y(other_bbox)
+            if other_center < line_center:
+                above_gaps.append(
+                    max(
+                        0.0,
+                        _effective_text_row_gap(
+                            (other_line, other_bbox),
+                            (line, bbox),
+                        ),
+                    )
+                )
+            elif other_center > line_center:
+                below_gaps.append(
+                    max(
+                        0.0,
+                        _effective_text_row_gap(
+                            (line, bbox),
+                            (other_line, other_bbox),
+                        ),
+                    )
+                )
+        output[line.source_index] = (
+            min(above_gaps) if above_gaps else None,
+            min(below_gaps) if below_gaps else None,
+        )
+    return output
+
+
+def _line_inside_visual_container(
+    line_bbox: BBox,
+    container_bboxes: list[BBox],
+) -> bool:
+    """检查文本行中心是否落入视觉容器，容器内标签不得借标题原型晋升。"""
+
+    center_x = _bbox_center_x(line_bbox)
+    center_y = _bbox_center_y(line_bbox)
+    return any(bbox[0] <= center_x <= bbox[2] and bbox[1] <= center_y <= bbox[3] for bbox in container_bboxes)
+
+
+def _line_near_visual_container(
+    line_bbox: BBox,
+    container_bboxes: list[BBox],
+    body_height: float,
+) -> bool:
+    """检查短行是否紧邻图、表等容器，以纯几何方式抑制 caption 误判。"""
+
+    for container_bbox in container_bboxes:
+        if _bbox_axis_overlap_ratio(line_bbox, container_bbox, axis="x") < 0.35:
+            continue
+        container_width = max(0.1, container_bbox[2] - container_bbox[0])
+        if line_bbox[2] - line_bbox[0] > 0.8 * container_width:
+            continue
+        vertical_gap = max(line_bbox[1] - container_bbox[3], container_bbox[1] - line_bbox[3], 0.0)
+        if vertical_gap <= 2.0 * body_height:
+            return True
+    return False
+
+
+__all__ = [
+    "_NUMBERED_SECTION_TITLE_RE",
+    "_SECTION_NUMBER_ONLY_RE",
+    "_SECTION_TITLE_TERMINAL_RE",
+    "_UNNUMBERED_SECTION_HEADING_RE",
+    "_build_physical_title_gap_map",
+    "_line_inside_visual_container",
+    "_line_near_visual_container",
+]

docvortex/analyzers/native/pdf/title_analysis/document_profile.py

@@ -0,0 +1,164 @@
+"""使用既有页面分类探测构建全文标题原型。"""
+
+from __future__ import annotations
+
+import statistics
+from dataclasses import replace
+from typing import Literal
+
+from ..geometry import _rotate_bbox_to_upright
+from ..line_layout import _infer_text_lanes, _line_effective_height, _normalized_font_family
+from ..models import _DocumentBodyProfile, _DocumentTitleProfile, _PreparedPage, _TitleStylePrototype
+from .common import _line_inside_visual_container
+from .page_titles import _classify_page_titles
+from .prototype import _title_profile_alignment, _title_profile_seed_matches_cluster
+
+
+def _infer_document_title_profile(
+    prepared_pages: list[_PreparedPage],
+    document_body_profile: _DocumentBodyProfile | None,
+) -> _DocumentTitleProfile | None:
+    """在副本上复用现有标题判定，并把跨页稳定样式聚成标题原型。"""
+
+    if document_body_profile is None:
+        return None
+    seeds: list[
+        tuple[
+            str,
+            int,
+            float,
+            float | None,
+            Literal["left", "center"],
+            float,
+            int,
+        ]
+    ] = []
+    for page_index, prepared in enumerate(prepared_pages):
+        probe_lines = [replace(line) for line in prepared.remaining_lines]
+        container_bboxes = [
+            block["bbox"] for block in prepared.fixed_blocks if not isinstance(block.get("_inline_visual_row_id"), int)
+        ]
+        _classify_page_titles(
+            probe_lines,
+            prepared.page_size,
+            page_index=page_index,
+            container_bboxes=container_bboxes,
+            document_body_profile=document_body_profile,
+        )
+        seen_rows: set[tuple[int, int]] = set()
+        for angle in sorted({line.angle for line in probe_lines}):
+            geometry = [
+                (
+                    line,
+                    _rotate_bbox_to_upright(
+                        line.bbox,
+                        prepared.page_size,
+                        angle,
+                    ),
+                )
+                for line in probe_lines
+                if line.angle == angle
+            ]
+            if not geometry:
+                continue
+            median_height = statistics.median(_line_effective_height(line, bbox) for line, bbox in geometry)
+            local_page_width = prepared.page_size[1] if angle in {90, 270} else prepared.page_size[0]
+            lanes = _infer_text_lanes(
+                geometry,
+                local_page_width,
+                median_height,
+            )
+            local_container_bboxes = [
+                _rotate_bbox_to_upright(
+                    bbox,
+                    prepared.page_size,
+                    angle,
+                )
+                for bbox in container_bboxes
+            ]
+            for lane in lanes:
+                for line, bbox in lane.lines:
+                    line_height_ratio = _line_effective_height(line, bbox) / document_body_profile.body_height
+                    large_unresolved_seed = (
+                        page_index > 0
+                        and line.semantic_type is None
+                        and line_height_ratio >= 1.3
+                        and bbox[2] - bbox[0] <= 0.8 * local_page_width
+                        and not _line_inside_visual_container(
+                            bbox,
+                            local_container_bboxes,
+                        )
+                    )
+                    if (
+                        (line.semantic_type != "paragraph_title" and not large_unresolved_seed)
+                        or line.font_signature is None
+                        or line.font_coverage < 0.75
+                    ):
+                        continue
+                    row_identity = line.visual_row_id if line.visual_row_id is not None else line.source_index
+                    row_key = (angle, row_identity)
+                    if row_key in seen_rows:
+                        continue
+                    alignment = _title_profile_alignment(
+                        bbox,
+                        lane,
+                        document_body_profile.body_height,
+                    )
+                    if alignment is None:
+                        continue
+                    font_family = _normalized_font_family(line.font_signature)
+                    if font_family is None:
+                        continue
+                    mode, anchor_offset = alignment
+                    seeds.append(
+                        (
+                            font_family,
+                            line.font_signature[1],
+                            line_height_ratio,
+                            line.dominant_font_weight,
+                            mode,
+                            anchor_offset,
+                            page_index,
+                        )
+                    )
+                    seen_rows.add(row_key)
+
+    clusters: list[list[tuple[str, int, float, float | None, Literal["left", "center"], float, int]]] = []
+    for seed in sorted(seeds, key=lambda item: (item[0], item[1], item[4], item[2])):
+        target = next(
+            (cluster for cluster in clusters if _title_profile_seed_matches_cluster(seed, cluster)),
+            None,
+        )
+        if target is None:
+            clusters.append([seed])
+        else:
+            target.append(seed)
+
+    prototypes: list[_TitleStylePrototype] = []
+    for cluster in clusters:
+        support_pages = len({seed[6] for seed in cluster})
+        if len(cluster) < 3 and support_pages < 2:
+            continue
+        weights = [seed[3] for seed in cluster if seed[3] is not None]
+        prototypes.append(
+            _TitleStylePrototype(
+                font_family=cluster[0][0],
+                font_flags=cluster[0][1],
+                height_ratio=statistics.median(seed[2] for seed in cluster),
+                weight=statistics.median(weights) if weights else None,
+                alignment=cluster[0][4],
+                anchor_offset=statistics.median(seed[5] for seed in cluster),
+                support_count=len(cluster),
+                support_pages=support_pages,
+            )
+        )
+    if not prototypes:
+        return None
+    prototypes.sort(
+        key=lambda item: (item.support_pages, item.support_count),
+        reverse=True,
+    )
+    return _DocumentTitleProfile(tuple(prototypes))
+
+
+__all__ = ["_infer_document_title_profile"]