Source symbols: mineru/backend/pipeline/pipeline_middle_json_mkcontent.py

Deterministic, value-free symbol metadata extracted from public source. Implementations and literal values are not copied into this page.

• Revision: master@79d6d8d79fb8f3ddba5cc34c07a16f0ec36f56c7 · 2026-07-17T07:32:08Z
• Declarations: 34
• Referenced calls: 62

Declared symbols

• make_blocks_to_markdown — def at line 18; references merge_para_with_text, get_title_level, len, get, merge_visual_blocks_to_markdown, strip, append, get_blocks_in_index_order, _inherit_parent_code_render_metadata, extend, render_visual_block_segments, get_visual_block_separator, sorted, enumerate, float, dict, _build_visual_details_block
• merge_visual_blocks_to_markdown — def at line 70; references get_blocks_in_index_order, get, _inherit_parent_code_render_metadata, extend, render_visual_block_segments, get_visual_block_separator, sorted, enumerate, float, dict, merge_para_with_text, strip, append, _build_visual_details_block
• get_blocks_in_index_order — def at line 91; references sorted, enumerate, get, float, dict, merge_para_with_text, strip, append, _build_visual_details_block
• _inherit_parent_code_render_metadata — def at line 103; references get, dict, merge_para_with_text, strip, append, _build_visual_details_block
• render_visual_block_segments — def at line 124; references merge_para_with_text, strip, get, append, _build_visual_details_block
• get_visual_block_separator — def at line 191; references get_latex_delimiter_config
• _prefix_table_img_src — def at line 224; references sub, _replace_eq_tags_in_table_html, isinstance, join, str, strip, _normalize_visual_content, get, _is_fenced_code_block, _merge_para_text, rstrip, split, escape_text_block_markdown_prefix, detect_lang, _collect_text_for_lang_detection, enumerate, _line_prefix, append, _render_span, _join_rendered_span
• _replace_eq_tags_in_table_html — def at line 236; references sub, _prefix_table_img_src, isinstance, join, str, strip, _normalize_visual_content, get, _is_fenced_code_block, _merge_para_text, rstrip, split, escape_text_block_markdown_prefix, detect_lang, _collect_text_for_lang_detection, enumerate, _line_prefix, append, _render_span, _join_rendered_span
• _format_embedded_html — def at line 251; references _replace_eq_tags_in_table_html, _prefix_table_img_src, isinstance, join, str, strip, _normalize_visual_content, get, _is_fenced_code_block, _merge_para_text, rstrip, split, escape_text_block_markdown_prefix, detect_lang, _collect_text_for_lang_detection, enumerate, _line_prefix, append, _render_span, _join_rendered_span
• _normalize_visual_content — def at line 256; references isinstance, join, str, strip, get, _is_fenced_code_block, _merge_para_text, rstrip, split, escape_text_block_markdown_prefix, detect_lang, _collect_text_for_lang_detection, enumerate, _line_prefix, append, _render_span, _join_rendered_span, _normalize_text_content, full_to_half_exclude_marks, escape_special_markdown_char
• _build_visual_details_block — def at line 265; references _normalize_visual_content, get, _is_fenced_code_block, _merge_para_text, join, rstrip, split, escape_text_block_markdown_prefix, detect_lang, _collect_text_for_lang_detection, enumerate, _line_prefix, append, _render_span, _join_rendered_span, _normalize_text_content, full_to_half_exclude_marks, escape_special_markdown_char, strip, len
• _apply_visual_sub_type — def at line 279; references get, _is_fenced_code_block, _merge_para_text, join, rstrip, split, escape_text_block_markdown_prefix, detect_lang, _collect_text_for_lang_detection, enumerate, _line_prefix, append, _render_span, _join_rendered_span, _normalize_text_content, full_to_half_exclude_marks, escape_special_markdown_char, strip, len, is_hyphen_at_line_end
• merge_para_with_text — def at line 286; references _is_fenced_code_block, _merge_para_text, join, rstrip, split, get, escape_text_block_markdown_prefix, detect_lang, _collect_text_for_lang_detection, enumerate, _line_prefix, append, _render_span, _join_rendered_span, _normalize_text_content, full_to_half_exclude_marks, escape_special_markdown_char, strip, len, is_hyphen_at_line_end
• _merge_para_text — def at line 305; references detect_lang, _collect_text_for_lang_detection, enumerate, _line_prefix, append, _render_span, _join_rendered_span, join, rstrip, get, _normalize_text_content, full_to_half_exclude_marks, escape_special_markdown_char, strip, len, is_hyphen_at_line_end, _next_line_starts_with_lowercase_text, bool, islower, list
• _is_fenced_code_block — def at line 341; references get, append, _normalize_text_content, join, full_to_half_exclude_marks, escape_special_markdown_char, strip, len, is_hyphen_at_line_end, _next_line_starts_with_lowercase_text, bool, islower, list
• _collect_text_for_lang_detection — def at line 348; references append, _normalize_text_content, get, join, full_to_half_exclude_marks, escape_special_markdown_char, strip, len, is_hyphen_at_line_end, _next_line_starts_with_lowercase_text, bool, islower, list
• _normalize_text_content — def at line 359; references full_to_half_exclude_marks, get, escape_special_markdown_char, strip, len, is_hyphen_at_line_end, _next_line_starts_with_lowercase_text, bool, islower, append, list
• _render_span — def at line 365; references _normalize_text_content, get, escape_special_markdown_char, strip, len, is_hyphen_at_line_end, _next_line_starts_with_lowercase_text, bool, islower, append, list
• _join_rendered_span — def at line 391; references len, is_hyphen_at_line_end, _next_line_starts_with_lowercase_text, get, _normalize_text_content, bool, islower, append, list
• _line_prefix — def at line 422; references get, len, _normalize_text_content, bool, islower, append, list
• _next_line_starts_with_lowercase_text — def at line 430; references len, get, _normalize_text_content, bool, islower, append, list
• merge_adjacent_ref_text_blocks_for_content — def at line 448; references len, append, list, get
• flush_ref_group — def at line 452; references len, append, list, get
• _build_bbox — def at line 478; references int, get, enumerate, append
• _get_ref_text_item_blocks — def at line 492; references get, enumerate, append
• _split_list_item_blocks — def at line 496; references enumerate, get, append
• _get_body_data — def at line 518; references get, _normalize_visual_content, get_data_from_spans, detect_lang, _collect_text_for_lang_detection, enumerate, _normalize_text_content, strip, len, is_hyphen_at_line_end, _next_line_starts_with_lowercase_text, append
• get_data_from_spans — def at line 519; references get, _normalize_visual_content, detect_lang, _collect_text_for_lang_detection, enumerate, _normalize_text_content, strip, len, is_hyphen_at_line_end, _next_line_starts_with_lowercase_text, append
• merge_para_with_text_v2 — def at line 550; references detect_lang, _collect_text_for_lang_detection, get, enumerate, _normalize_text_content, strip, len, is_hyphen_at_line_end, _next_line_starts_with_lowercase_text, append
• make_blocks_to_content_list — def at line 609; references merge_para_with_text
• make_blocks_to_content_list_v2 — def at line 745; references ValueError, merge_para_with_text_v2
• union_make — def at line 968; references get, make_blocks_to_markdown, extend, merge_adjacent_ref_text_blocks_for_content, make_blocks_to_content_list, append, make_blocks_to_content_list_v2, join, error
• get_title_level — def at line 1014; references get
• escape_special_markdown_char — def at line 1021; references escape_conservative_markdown_text

File-level call references

• import — line 12
• merge_para_with_text — line 33
• get_title_level — line 35
• len — line 38
• get — line 40
• merge_visual_blocks_to_markdown — line 48
• strip — line 62
• append — line 65
• get_blocks_in_index_order — line 76
• _inherit_parent_code_render_metadata — line 77
• extend — line 78
• render_visual_block_segments — line 78
• get_visual_block_separator — line 84
• sorted — line 96
• enumerate — line 97
• float — line 98
• dict — line 116
• _build_visual_details_block — line 157
• _format_embedded_html — line 181
• get_latex_delimiter_config — line 207
• sub — line 229
• _replace_eq_tags_in_table_html — line 253
• _prefix_table_img_src — line 253
• isinstance — line 258
• join — line 259
• str — line 259
• _normalize_visual_content — line 267
• _is_fenced_code_block — line 287
• _merge_para_text — line 288
• rstrip — line 295
• split — line 295
• escape_text_block_markdown_prefix — line 301
• detect_lang — line 311
• _collect_text_for_lang_detection — line 311
• _line_prefix — line 315
• _render_span — line 320
• _join_rendered_span — line 325
• _normalize_text_content — line 355
• full_to_half_exclude_marks — line 362
• escape_special_markdown_char — line 374
• is_hyphen_at_line_end — line 413
• _next_line_starts_with_lowercase_text — line 415
• bool — line 445
• islower — line 445
• list — line 461
• flush_ref_group — line 471
• int — line 485
• get_data_from_spans — line 542
• _get_ref_text_item_blocks — line 639
• _get_body_data — line 663
• _apply_visual_sub_type — line 668
• _build_bbox — line 737
• ValueError — line 767
• merge_para_with_text_v2 — line 771
• count — line 836
• _split_list_item_blocks — line 927
• make_blocks_to_markdown — line 981
• merge_adjacent_ref_text_blocks_for_content — line 984
• make_blocks_to_content_list — line 990
• make_blocks_to_content_list_v2 — line 1000
• error — line 1010
• escape_conservative_markdown_text — line 1025

Source: mineru/backend/pipeline/pipeline_middle_json_mkcontent.py