guidebook 0.1.37

HonKit/GitBook compatible static book generator
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
use pulldown_cmark::{html, Event, Options, Parser, Tag, TagEnd, CodeBlockKind, HeadingLevel};
use std::path::Path;

/// Table of Contents item
#[derive(Debug, Clone)]
pub struct TocItem {
    pub level: u8,
    pub text: String,
    pub id: String,
}

/// Extract headings from markdown content for TOC generation
pub fn extract_headings(content: &str) -> Vec<TocItem> {
    let content = fix_fullwidth_heading_spaces(content);

    let mut options = Options::empty();
    options.insert(Options::ENABLE_TABLES);
    options.insert(Options::ENABLE_FOOTNOTES);
    options.insert(Options::ENABLE_STRIKETHROUGH);
    options.insert(Options::ENABLE_TASKLISTS);
    options.insert(Options::ENABLE_HEADING_ATTRIBUTES);

    let parser = Parser::new_ext(&content, options);

    let mut headings = Vec::new();
    let mut in_heading: Option<HeadingLevel> = None;
    let mut heading_text = String::new();

    for event in parser {
        match &event {
            Event::Start(Tag::Heading { level, .. }) => {
                in_heading = Some(*level);
                heading_text.clear();
            }
            Event::Text(text) if in_heading.is_some() => {
                heading_text.push_str(text);
            }
            Event::End(TagEnd::Heading(level)) if in_heading.is_some() => {
                let level_num = heading_level_to_num(*level);
                // Only include h2, h3, h4 in TOC (skip h1 which is page title)
                if level_num >= 2 && level_num <= 4 {
                    let id = slugify(&heading_text);
                    headings.push(TocItem {
                        level: level_num,
                        text: heading_text.clone(),
                        id,
                    });
                }
                in_heading = None;
            }
            _ => {}
        }
    }

    headings
}

/// Render markdown content to HTML with Mermaid support
/// current_path: the path of the current markdown file (e.g., "Customer/AssetStatus/PortfolioTop.md")
/// hardbreaks: when true, treat single newlines as hard breaks (<br>)
pub fn render_markdown_with_path(content: &str, current_path: Option<&str>, hardbreaks: bool) -> String {
    let html = render_markdown_internal(content, hardbreaks);

    // If we have a current path, convert relative links to absolute
    if let Some(path) = current_path {
        convert_relative_links_to_absolute(&html, path)
    } else {
        html
    }
}

/// Render markdown content to HTML (backward compatible)
pub fn render_markdown(content: &str) -> String {
    render_markdown_internal(content, false)
}

/// Render markdown content to HTML with hardbreaks option
pub fn render_markdown_with_hardbreaks(content: &str, hardbreaks: bool) -> String {
    render_markdown_internal(content, hardbreaks)
}

fn render_markdown_internal(content: &str, hardbreaks: bool) -> String {
    // Preprocess: fix full-width spaces after heading markers
    let content = fix_fullwidth_heading_spaces(content);
    // Preprocess: fix image paths with spaces
    let content = fix_image_paths_with_spaces(&content);
    // Preprocess: fix multi-line footnotes without proper indentation
    let content = fix_multiline_footnotes(&content);
    // Preprocess: fix malformed table separator rows
    let content = fix_table_separator_columns(&content);

    // Convert footnote definitions to inline format (preserve original position)
    let content = convert_footnote_definitions_inline(&content, hardbreaks);

    // Convert footnote references [^n] to placeholders BEFORE markdown parsing
    // This prevents [A][^1] from being interpreted as a markdown link reference
    let content = convert_footnote_references_to_placeholder(&content);

    let mut options = Options::empty();
    options.insert(Options::ENABLE_TABLES);
    // Don't use pulldown-cmark's footnote processing - we handle it ourselves
    // options.insert(Options::ENABLE_FOOTNOTES);
    options.insert(Options::ENABLE_STRIKETHROUGH);
    options.insert(Options::ENABLE_TASKLISTS);
    options.insert(Options::ENABLE_HEADING_ATTRIBUTES);

    let parser = Parser::new_ext(&content, options);

    // Process events to handle mermaid code blocks and heading IDs
    let mut in_mermaid = false;
    let mut mermaid_content = String::new();
    let mut in_heading: Option<HeadingLevel> = None;
    let mut heading_text = String::new();
    let mut events: Vec<Event> = Vec::new();

    for event in parser {
        match &event {
            Event::Start(Tag::CodeBlock(CodeBlockKind::Fenced(lang))) => {
                let lang_str = lang.as_ref();
                if lang_str == "mermaid" || lang_str.starts_with("mermaid") {
                    in_mermaid = true;
                    mermaid_content.clear();
                    continue;
                }
            }
            Event::End(TagEnd::CodeBlock) if in_mermaid => {
                // Output mermaid div instead of code block
                let mermaid_html = format!(
                    r#"<div class="mermaid">{}</div>"#,
                    html_escape(&mermaid_content)
                );
                events.push(Event::Html(mermaid_html.into()));
                in_mermaid = false;
                continue;
            }
            Event::Text(text) if in_mermaid => {
                mermaid_content.push_str(text);
                continue;
            }
            // Track heading start
            Event::Start(Tag::Heading { level, .. }) => {
                in_heading = Some(*level);
                heading_text.clear();
                events.push(event);
                continue;
            }
            // Capture heading text
            Event::Text(text) if in_heading.is_some() => {
                heading_text.push_str(text);
                events.push(event);
                continue;
            }
            // End of heading: inject ID
            Event::End(TagEnd::Heading(level)) if in_heading.is_some() => {
                let id = slugify(&heading_text);
                let level_num = heading_level_to_num(*level);
                // Pop the heading content and rebuild with ID
                let mut heading_events = Vec::new();
                while let Some(ev) = events.pop() {
                    if matches!(ev, Event::Start(Tag::Heading { .. })) {
                        break;
                    }
                    heading_events.push(ev);
                }
                heading_events.reverse();

                // Push heading with ID as raw HTML
                let open_tag = format!(r#"<h{} id="{}">"#, level_num, id);
                events.push(Event::Html(open_tag.into()));
                events.extend(heading_events);
                events.push(Event::Html(format!("</h{}>", level_num).into()));

                in_heading = None;
                continue;
            }
            // Convert soft breaks to hard breaks when hardbreaks option is enabled
            Event::SoftBreak if hardbreaks => {
                events.push(Event::HardBreak);
                continue;
            }
            _ => {}
        }
        events.push(event);
    }

    let mut html_output = String::new();
    html::push_html(&mut html_output, events.into_iter());

    // Fix relative links: convert .md to .html
    html_output = fix_relative_links(&html_output);

    // Auto-link URLs that are not already linked
    html_output = autolink_urls(&html_output);

    // Convert any remaining markdown images inside HTML blocks to <img> tags
    html_output = convert_remaining_markdown_images(&html_output);

    // Convert footnote placeholders to HTML
    html_output = convert_footnote_placeholders_to_html(&html_output);

    html_output
}

fn heading_level_to_num(level: HeadingLevel) -> u8 {
    match level {
        HeadingLevel::H1 => 1,
        HeadingLevel::H2 => 2,
        HeadingLevel::H3 => 3,
        HeadingLevel::H4 => 4,
        HeadingLevel::H5 => 5,
        HeadingLevel::H6 => 6,
    }
}

/// Generate a URL-safe slug from text (matching github-slugger / HonKit behavior)
fn slugify(text: &str) -> String {
    text.to_lowercase()
        .chars()
        .filter_map(|c| {
            if c.is_alphanumeric() || c == '-' || c == '_' {
                Some(c)
            } else if c.is_whitespace() {
                Some('-')
            } else if c > '\x7F' {
                // Keep non-ASCII characters (Japanese, etc.)
                Some(c)
            } else {
                // Remove other special characters (/, ., etc.) to match github-slugger
                None
            }
        })
        .collect::<String>()
        .split('-')
        .filter(|s| !s.is_empty())
        .collect::<Vec<_>>()
        .join("-")
}

fn html_escape(s: &str) -> String {
    s.replace('&', "&amp;")
        .replace('<', "&lt;")
        .replace('>', "&gt;")
        .replace('"', "&quot;")
}


/// Convert footnote definitions in-place to HTML (preserve original position)
fn convert_footnote_definitions_inline(content: &str, hardbreaks: bool) -> String {
    let mut result_lines = Vec::new();
    let lines: Vec<&str> = content.lines().collect();
    let mut i = 0;

    while i < lines.len() {
        let line = lines[i];
        // Check if this line starts a footnote definition [^n]:
        if let Some(captures) = parse_footnote_def_start(line) {
            let (number, first_line_content) = captures;
            // Trim trailing whitespace from first line (for hardbreaks consistency)
            let first_line_content = first_line_content.trim_end();
            let mut continuation_lines: Vec<String> = Vec::new();

            // Collect continuation lines (indented or list items until next footnote/heading/blank)
            i += 1;
            while i < lines.len() {
                let next_line = lines[i];
                let trimmed = next_line.trim_start();

                // Stop if: empty line, new footnote, heading
                if trimmed.is_empty() {
                    break;
                }
                if trimmed.starts_with("[^") && trimmed.contains("]:") {
                    break;
                }
                if trimmed.starts_with('#') {
                    break;
                }

                // This is a continuation line
                continuation_lines.push(next_line.to_string());
                i += 1;
            }

            // Convert to inline HTML at original position (HonKit style)
            // First line goes inline with number, return link right after first line
            // Then continuation content (lists, etc.) follows
            let return_link = format!(
                "<a href=\"#reffn_{}\" title=\"Jump back to footnote [{}] in the text.\"> ↩</a>",
                number, number
            );

            if continuation_lines.is_empty() {
                // Single-line footnote: <sup>n</sup>. content ↩
                result_lines.push(format!(
                    "<blockquote id=\"fn_{}\"><sup>{}</sup>. {}{}</blockquote>",
                    number, number, first_line_content, return_link
                ));
            } else {
                // Multi-line footnote: first line with return link, then rest as markdown
                let continuation_content = continuation_lines.join("\n");
                let continuation_html = render_footnote_continuation(&continuation_content, hardbreaks);
                result_lines.push(format!(
                    "<blockquote id=\"fn_{}\"><sup>{}</sup>. {}{}\n{}</blockquote>",
                    number, number, first_line_content, return_link, continuation_html
                ));
            }
        } else {
            result_lines.push(line.to_string());
            i += 1;
        }
    }

    result_lines.join("\n")
}

/// Convert footnote references [^n] to placeholder (before parsing)
/// Placeholder format: %%FNREF_n%% - will be converted to HTML after markdown parsing
fn convert_footnote_references_to_placeholder(content: &str) -> String {
    let mut result = String::new();
    let mut chars = content.char_indices().peekable();

    while let Some((i, c)) = chars.next() {
        if c == '[' && content[i..].starts_with("[^") {
            // Find the closing ]
            let rest = &content[i + 2..];
            if let Some(end) = rest.find(']') {
                let number = &rest[..end];
                // Make sure it's a reference (not a definition - no : after ])
                let after = &rest[end + 1..];
                if !after.starts_with(':') && !number.is_empty() && number.chars().all(|c| c.is_alphanumeric()) {
                    // This is a reference, convert to placeholder
                    result.push_str(&format!("%%FNREF_{}%%", number));
                    // Skip past the reference: ^number]
                    // We already consumed '[', so skip: ^ + number + ]
                    for _ in 0..(1 + end + 1) {
                        chars.next();
                    }
                    continue;
                }
            }
        }
        result.push(c);
    }

    result
}

/// Convert footnote placeholders to HTML (after markdown parsing)
fn convert_footnote_placeholders_to_html(html: &str) -> String {
    let mut result = html.to_string();
    // Find all %%FNREF_n%% patterns and replace with HTML
    let re_pattern = "%%FNREF_";
    while let Some(start) = result.find(re_pattern) {
        let after_prefix = &result[start + re_pattern.len()..];
        if let Some(end) = after_prefix.find("%%") {
            let number = &after_prefix[..end];
            let replacement = format!(
                "<sup><a href=\"#fn_{}\" id=\"reffn_{}\">{}</a></sup>",
                number, number, number
            );
            let full_placeholder = format!("%%FNREF_{}%%", number);
            result = result.replacen(&full_placeholder, &replacement, 1);
        } else {
            break;
        }
    }
    result
}

/// Parse a footnote definition start line, returns (number, rest_of_line)
fn parse_footnote_def_start(line: &str) -> Option<(&str, &str)> {
    let trimmed = line.trim_start();
    if !trimmed.starts_with("[^") {
        return None;
    }

    // Find the closing ]
    let after_bracket = &trimmed[2..];
    let end_bracket = after_bracket.find("]:")?;
    let number = &after_bracket[..end_bracket];

    // Get the content after ]:
    let rest = &after_bracket[end_bracket + 2..].trim_start();
    Some((number, rest))
}


/// Render footnote continuation content (lists, paragraphs after first line)
fn render_footnote_continuation(content: &str, hardbreaks: bool) -> String {
    // Find minimum indentation (excluding empty lines) to preserve relative indentation
    let min_indent = content
        .lines()
        .filter(|line| !line.trim().is_empty())
        .map(|line| line.len() - line.trim_start().len())
        .min()
        .unwrap_or(0);

    // Remove only the common leading indentation, preserving relative structure
    let dedented: String = content
        .lines()
        .map(|line| {
            if line.len() >= min_indent {
                &line[min_indent..]
            } else {
                line.trim_start()
            }
        })
        .collect::<Vec<_>>()
        .join("\n");

    let mut options = Options::empty();
    options.insert(Options::ENABLE_TABLES);
    options.insert(Options::ENABLE_STRIKETHROUGH);

    let parser = Parser::new_ext(&dedented, options);

    // Apply hardbreaks conversion if enabled
    let events: Vec<Event> = parser.map(|event| {
        if hardbreaks {
            match event {
                Event::SoftBreak => Event::HardBreak,
                _ => event,
            }
        } else {
            event
        }
    }).collect();

    let mut html = String::new();
    html::push_html(&mut html, events.into_iter());

    html.trim().to_string()
}


/// Fix multi-line footnotes without proper indentation
/// Adds 4 spaces to ALL continuation lines to preserve relative indentation structure
fn fix_multiline_footnotes(content: &str) -> String {
    let lines: Vec<&str> = content.lines().collect();
    let mut result = Vec::new();
    let mut in_footnote = false;

    for line in lines {
        // Check if this line starts a new footnote definition
        if line.starts_with("[^") && line.contains("]:") {
            in_footnote = true;
            result.push(line.to_string());
        } else if in_footnote {
            let trimmed = line.trim_start();

            if trimmed.is_empty() {
                // Empty line ends the footnote
                in_footnote = false;
                result.push(line.to_string());
            } else if trimmed.starts_with("[^") && trimmed.contains("]:") {
                // New footnote starts
                in_footnote = true;
                result.push(line.to_string());
            } else if trimmed.starts_with('#') {
                // Heading starts - end of footnotes section
                in_footnote = false;
                result.push(line.to_string());
            } else {
                // Continuation line - add 4 spaces to ALL lines to preserve relative structure
                result.push(format!("    {}", line));
            }
        } else {
            result.push(line.to_string());
        }
    }

    result.join("\n")
}

/// Fix malformed table rows:
/// - Add missing trailing | to header rows
/// - Fix separator rows where column count doesn't match header
fn fix_table_separator_columns(content: &str) -> String {
    let lines: Vec<&str> = content.lines().collect();
    let mut result = Vec::new();
    let mut i = 0;

    while i < lines.len() {
        let line = lines[i];
        let trimmed = line.trim();

        // Check if this line looks like a table row (starts with |)
        if trimmed.starts_with('|') {
            // Check if next line is a separator row
            if i + 1 < lines.len() {
                let next_line = lines[i + 1];
                if is_table_separator_row(next_line) {
                    // This is a header row - fix missing trailing pipe if needed
                    let fixed_header = fix_table_row_trailing_pipe(line);
                    let header_cols = count_table_columns(&fixed_header);

                    let separator_cols = count_table_columns(next_line);

                    // Push the fixed header
                    result.push(fixed_header);
                    i += 1;

                    // If column counts don't match, fix the separator row
                    if header_cols > 0 && separator_cols != header_cols {
                        let fixed_separator = generate_separator_row(header_cols, next_line);
                        result.push(fixed_separator);
                    } else {
                        result.push(next_line.to_string());
                    }
                    i += 1;
                    continue;
                }
            }
        }

        result.push(line.to_string());
        i += 1;
    }

    result.join("\n")
}

/// Add trailing pipe to table row if missing
fn fix_table_row_trailing_pipe(line: &str) -> String {
    let trimmed = line.trim();
    if trimmed.starts_with('|') && !trimmed.ends_with('|') {
        format!("{}|", line)
    } else {
        line.to_string()
    }
}

/// Count the number of columns in a table row
fn count_table_columns(line: &str) -> usize {
    let trimmed = line.trim();
    if !trimmed.starts_with('|') {
        return 0;
    }

    // Count the | characters, accounting for leading/trailing pipes
    let pipe_count = trimmed.chars().filter(|&c| c == '|').count();

    // Number of columns = pipes - 1 (for |col1|col2|col3| format)
    if pipe_count > 1 {
        pipe_count - 1
    } else {
        0
    }
}

/// Check if a line is a table separator row (contains only |, -, :, and whitespace)
fn is_table_separator_row(line: &str) -> bool {
    let trimmed = line.trim();
    if !trimmed.starts_with('|') || !trimmed.ends_with('|') {
        return false;
    }

    // Must contain at least one dash
    if !trimmed.contains('-') {
        return false;
    }

    // All characters must be |, -, :, or whitespace
    trimmed.chars().all(|c| c == '|' || c == '-' || c == ':' || c.is_whitespace())
}

/// Generate a separator row with the specified number of columns
/// Tries to preserve alignment style from the original separator
fn generate_separator_row(col_count: usize, original: &str) -> String {
    // Detect alignment style from original
    let alignment = if original.contains(":--:") || original.contains(":-:") {
        ":--:"
    } else if original.contains(":--") || original.contains(":-") {
        ":--"
    } else if original.contains("--:") || original.contains("-:") {
        "--:"
    } else {
        "--"
    };

    let cols: Vec<&str> = std::iter::repeat(alignment).take(col_count).collect();
    format!("|{}|", cols.join("|"))
}

/// Fix full-width spaces after heading markers (common mistake in Japanese documents)
/// Converts "## 見出し" to "## 見出し"
fn fix_fullwidth_heading_spaces(content: &str) -> String {
    content
        .lines()
        .map(|line| {
            // Check if line starts with heading markers followed by full-width space
            let trimmed = line.trim_start();
            if trimmed.starts_with('#') {
                // Find where the # sequence ends
                let hash_count = trimmed.chars().take_while(|&c| c == '#').count();
                if hash_count > 0 && hash_count <= 6 {
                    let after_hashes = &trimmed[hash_count..];
                    // Check if followed by full-width space (U+3000)
                    if after_hashes.starts_with('\u{3000}') {
                        // Replace full-width space with half-width space
                        let leading_whitespace = &line[..line.len() - trimmed.len()];
                        let rest = &after_hashes['\u{3000}'.len_utf8()..];
                        return format!("{}{} {}", leading_whitespace, "#".repeat(hash_count), rest);
                    }
                }
            }
            line.to_string()
        })
        .collect::<Vec<_>>()
        .join("\n")
}

/// Fix image paths that contain spaces by wrapping them in angle brackets
/// Converts ![alt](path with space.png) to ![alt](<path with space.png>)
fn fix_image_paths_with_spaces(content: &str) -> String {
    let mut result = String::new();
    let mut chars = content.chars().peekable();

    while let Some(c) = chars.next() {
        if c == '!' {
            // Check for image syntax: ![...](...)
            if chars.peek() == Some(&'[') {
                // Collect the entire potential image syntax
                let mut img_str = String::from("!");
                img_str.push(chars.next().unwrap()); // '['

                // Read alt text until ']'
                let mut bracket_depth = 1;
                while let Some(&ch) = chars.peek() {
                    img_str.push(chars.next().unwrap());
                    if ch == '[' {
                        bracket_depth += 1;
                    } else if ch == ']' {
                        bracket_depth -= 1;
                        if bracket_depth == 0 {
                            break;
                        }
                    }
                }

                // Check for '(' after ']'
                if chars.peek() == Some(&'(') {
                    img_str.push(chars.next().unwrap()); // '('

                    // Read URL until ')'
                    let mut url = String::new();
                    let mut paren_depth = 1;
                    while let Some(&ch) = chars.peek() {
                        if ch == '(' {
                            paren_depth += 1;
                            url.push(chars.next().unwrap());
                        } else if ch == ')' {
                            paren_depth -= 1;
                            if paren_depth == 0 {
                                chars.next(); // consume ')'
                                break;
                            }
                            url.push(chars.next().unwrap());
                        } else {
                            url.push(chars.next().unwrap());
                        }
                    }

                    // Check if URL contains spaces and doesn't already use angle brackets
                    if url.contains(' ') && !url.starts_with('<') {
                        img_str.push('<');
                        img_str.push_str(&url);
                        img_str.push('>');
                    } else {
                        img_str.push_str(&url);
                    }
                    img_str.push(')');
                }

                result.push_str(&img_str);
            } else {
                result.push(c);
            }
        } else {
            result.push(c);
        }
    }

    result
}

fn fix_relative_links(html: &str) -> String {
    // Replace .md links with .html
    // Pattern: href="...*.md" or href='...*.md'
    let mut result = html.to_string();

    // Simple regex-like replacement for .md links
    // This handles href="path.md" and href="path.md#anchor"
    let patterns = [
        (r#".md""#, r#".html""#),
        (r#".md#"#, r#".html#"#),
        (r#".md'"#, r#".html'"#),
    ];

    for (from, to) in patterns {
        result = result.replace(from, to);
    }

    result
}

/// Auto-link URLs that are not already inside anchor tags or code blocks
/// Converts bare URLs like https://example.com to <a href="..." target="_blank">...</a>
fn autolink_urls(html: &str) -> String {
    let mut result = String::new();
    let mut chars = html.char_indices().peekable();
    let mut in_code = false;  // Track if we're inside <code> or <pre>

    while let Some((i, c)) = chars.next() {
        // Check if we're inside an HTML tag
        if c == '<' {
            result.push(c);

            // Collect the tag
            let mut tag_content = String::new();
            while let Some((_, ch)) = chars.next() {
                result.push(ch);
                if ch == '>' {
                    break;
                }
                tag_content.push(ch);
            }

            // Check for code/pre tags
            let tag_lower = tag_content.to_lowercase();
            if tag_lower.starts_with("code") || tag_lower.starts_with("pre") {
                in_code = true;
            } else if tag_lower.starts_with("/code") || tag_lower.starts_with("/pre") {
                in_code = false;
            }
            continue;
        }

        // Skip auto-linking if inside code block
        if in_code {
            result.push(c);
            continue;
        }

        // Check for http:// or https://
        if c == 'h' && html[i..].starts_with("http://") || html[i..].starts_with("https://") {
            // Check if this URL is already inside an href=""
            if result.ends_with("href=\"") || result.ends_with("src=\"") {
                // Already in an href, just copy normally
                result.push(c);
                continue;
            }

            // Extract the URL
            let url_start = i;
            let mut url_end = i + 1;

            // Continue consuming URL characters
            while let Some(&(next_i, next_c)) = chars.peek() {
                // URL ends at whitespace, <, >, ", '
                if next_c.is_whitespace() || next_c == '<' || next_c == '>'
                    || next_c == '"' || next_c == '\'' {
                    break;
                }
                url_end = next_i + next_c.len_utf8();
                chars.next();
            }

            let mut url = &html[url_start..url_end];

            // Remove trailing punctuation that's likely not part of URL
            while url.ends_with('.') || url.ends_with(',') || url.ends_with(';')
                || url.ends_with(':') || url.ends_with(')') || url.ends_with('!') || url.ends_with('?') {
                url = &url[..url.len() - 1];
            }

            // Create the link with target="_blank"
            result.push_str(&format!(
                r#"<a href="{}" target="_blank">{}</a>"#,
                url, url
            ));

            // If we trimmed trailing punctuation, add it back
            let trimmed_len = url_end - url_start - url.len();
            if trimmed_len > 0 {
                result.push_str(&html[url_start + url.len()..url_end]);
            }
        } else {
            result.push(c);
        }
    }

    result
}

/// Convert remaining markdown image syntax ![alt](url) to <img> tags
/// This handles images inside raw HTML blocks that pulldown-cmark doesn't parse
/// Skips content inside <code> and <pre> tags
fn convert_remaining_markdown_images(html: &str) -> String {
    let mut result = String::new();
    let mut chars = html.char_indices().peekable();
    let mut in_code = false;  // Track if we're inside <code> or <pre>

    while let Some((_, c)) = chars.next() {
        // Check if we're inside an HTML tag
        if c == '<' {
            result.push(c);

            // Collect the tag
            let mut tag_content = String::new();
            while let Some((_, ch)) = chars.next() {
                result.push(ch);
                if ch == '>' {
                    break;
                }
                tag_content.push(ch);
            }

            // Check for code/pre tags
            let tag_lower = tag_content.to_lowercase();
            if tag_lower.starts_with("code") || tag_lower.starts_with("pre") {
                in_code = true;
            } else if tag_lower.starts_with("/code") || tag_lower.starts_with("/pre") {
                in_code = false;
            }
            continue;
        }

        // Skip image conversion if inside code block
        if in_code {
            result.push(c);
            continue;
        }

        if c == '!' && chars.peek().map(|(_, ch)| *ch) == Some('[') {
            chars.next(); // consume '['

            // Collect alt text until ']'
            let mut alt = String::new();
            let mut bracket_depth = 1;
            while let Some((_, ch)) = chars.next() {
                if ch == '[' {
                    bracket_depth += 1;
                    alt.push(ch);
                } else if ch == ']' {
                    bracket_depth -= 1;
                    if bracket_depth == 0 {
                        break;
                    }
                    alt.push(ch);
                } else {
                    alt.push(ch);
                }
            }

            // Check for '(' after ']'
            if chars.peek().map(|(_, ch)| *ch) == Some('(') {
                chars.next(); // consume '('

                // Collect URL until ')'
                let mut url = String::new();
                let mut paren_depth = 1;
                while let Some((_, ch)) = chars.next() {
                    if ch == '(' {
                        paren_depth += 1;
                        url.push(ch);
                    } else if ch == ')' {
                        paren_depth -= 1;
                        if paren_depth == 0 {
                            break;
                        }
                        url.push(ch);
                    } else {
                        url.push(ch);
                    }
                }

                // Output as <img> tag
                result.push_str(&format!(r#"<img src="{}" alt="{}">"#, url, alt));
            } else {
                // Not an image, output as-is
                result.push('!');
                result.push('[');
                result.push_str(&alt);
                result.push(']');
            }
        } else {
            result.push(c);
        }
    }

    result
}

/// Convert internal links to proper relative paths from current file
/// Links like "Customer/AssetStatus/PortfolioStock.html" (relative from book root)
/// need to be converted to "../../Customer/AssetStatus/PortfolioStock.html"
/// when rendered from a file at "Customer/AssetStatus/PortfolioTop.html"
/// current_path: e.g., "Customer/AssetStatus/PortfolioTop.md"
fn convert_relative_links_to_absolute(html: &str, current_path: &str) -> String {
    let result = html.to_string();

    // Calculate the depth (number of directories from root)
    // e.g., "Customer/AssetStatus/PortfolioTop.md" -> depth 2
    let depth = Path::new(current_path)
        .parent()
        .map(|p| {
            let dir = p.to_string_lossy();
            if dir.is_empty() {
                0
            } else {
                dir.matches('/').count() + 1
            }
        })
        .unwrap_or(0);

    // Create the prefix to go back to root (e.g., "../../" for depth 2)
    let root_prefix: String = "../".repeat(depth);

    // Find and replace href="..." patterns
    let mut new_result = String::new();
    let mut last_end = 0;

    // Process href="..." patterns
    let href_pattern = r#"href=""#;
    let mut search_start = 0;

    while let Some(href_pos) = result[search_start..].find(href_pattern) {
        let abs_href_pos = search_start + href_pos;
        let url_start = abs_href_pos + href_pattern.len();

        // Find the closing quote
        if let Some(url_end_offset) = result[url_start..].find('"') {
            let url_end = url_start + url_end_offset;
            let url = &result[url_start..url_end];

            // Check if this is an internal link that needs conversion
            // Skip: external links (http/https), anchor-only (#), already relative (../ or ./), absolute (/)
            let needs_conversion = !url.is_empty()
                && !url.starts_with("http://")
                && !url.starts_with("https://")
                && !url.starts_with('#')
                && !url.starts_with("../")
                && !url.starts_with("./")
                && !url.starts_with('/')
                && !url.starts_with("mailto:")
                && !url.starts_with("javascript:")
                && depth > 0;

            if needs_conversion {
                // Copy everything up to the URL
                new_result.push_str(&result[last_end..url_start]);
                // Add the root prefix + original URL
                new_result.push_str(&root_prefix);
                new_result.push_str(url);
                last_end = url_end;
            }

            search_start = url_end + 1;
        } else {
            search_start = url_start + 1;
        }
    }

    // Copy the remaining part
    new_result.push_str(&result[last_end..]);

    new_result
}


#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_render_basic_markdown() {
        let md = "# Hello\n\nThis is a **test**.";
        let html = render_markdown(md);
        // Heading now includes ID attribute
        assert!(html.contains("<h1 id=\"hello\">Hello</h1>"), "HTML: {}", html);
        assert!(html.contains("<strong>test</strong>"));
    }

    #[test]
    fn test_render_table() {
        let md = r#"
| Header 1 | Header 2 |
|----------|----------|
| Cell 1   | Cell 2   |
"#;
        let html = render_markdown(md);
        assert!(html.contains("<table>"));
        assert!(html.contains("<th>Header 1</th>"));
    }

    #[test]
    fn test_render_mermaid() {
        let md = r#"
```mermaid
sequenceDiagram
    A->>B: Hello
```
"#;
        let html = render_markdown(md);
        assert!(html.contains(r#"<div class="mermaid">"#));
        assert!(html.contains("sequenceDiagram"));
    }

    #[test]
    fn test_fix_relative_links() {
        let html = r#"<a href="chapter1.md">Link</a>"#;
        let fixed = fix_relative_links(html);
        assert!(fixed.contains(r#"href="chapter1.html""#));
    }

    #[test]
    fn test_image_in_table() {
        let md = r#"
| Col1 | Col2 |
|:--:|:--:|
|![](test.png)|text|
"#;
        let html = render_markdown(md);
        println!("Generated HTML: {}", html);
        assert!(html.contains("<img"), "Image tag should be generated: {}", html);
    }

    #[test]
    fn test_image_in_table_japanese() {
        let md = r#"## デザイン
|該当するタイムラインがある場合|該当するタイムラインがない場合|
|:--:|:--:|
|![](../../../assets/Customer/TimeLine/B-0-8-Timeline Information Page.png)|![](../../../assets/Customer/TimeLine/B-0-8-Timeline Information Page0件.png)|
## 項目一覧"#;
        let html = render_markdown(md);
        println!("Generated HTML: {}", html);
        assert!(html.contains("<img"), "Image tag should be generated: {}", html);
    }

    #[test]
    fn test_image_with_space_in_filename() {
        // Test: space in filename
        let md = r#"|![](test file.png)|"#;
        let html = render_markdown(md);
        println!("With space: {}", html);

        // Test: no space in filename
        let md2 = r#"|![](testfile.png)|"#;
        let html2 = render_markdown(md2);
        println!("No space: {}", html2);
    }

    #[test]
    fn test_autolink_urls() {
        // Test: bare URL should become a link
        let md = "Guide Git:https://github.com/guide-inc-org/kcmsr-member-site-spec";
        let html = render_markdown(md);
        println!("Autolink result: {}", html);
        assert!(html.contains(r#"<a href="https://github.com/guide-inc-org/kcmsr-member-site-spec" target="_blank">"#),
            "URL should be auto-linked: {}", html);
    }

    #[test]
    fn test_autolink_does_not_double_link() {
        // Test: already linked URL should not be double-linked
        let md = "[Link](https://example.com)";
        let html = render_markdown(md);
        println!("Already linked result: {}", html);
        // Should have exactly one href for the URL
        let count = html.matches("https://example.com").count();
        assert_eq!(count, 1, "URL should appear only once: {}", html);
    }

    #[test]
    fn test_multiline_footnotes() {
        let md = r#"Text with footnote[^1].

[^1]: First line
- Second line
- Third line
[^2]: Another footnote"#;
        let html = render_markdown(md);
        println!("Footnote HTML: {}", html);
        // The footnote should be properly rendered with list items inside
        assert!(html.contains("<li>"), "Footnote should contain list items: {}", html);
    }

    #[test]
    fn test_fix_multiline_footnotes_preprocessing() {
        let input = r#"[^1]: First line
- Second line
- Third line
[^2]: Another"#;
        let output = fix_multiline_footnotes(input);
        println!("Preprocessed:\n{}", output);
        assert!(output.contains("    - Second line"), "Second line should be indented: {}", output);
        assert!(output.contains("    - Third line"), "Third line should be indented: {}", output);
        assert!(!output.contains("    [^2]"), "New footnote should not be indented: {}", output);
    }

    #[test]
    fn test_slugify_matches_github_slugger() {
        // Test that slugify matches github-slugger / HonKit behavior
        // Special characters like / should be removed, not converted to hyphens
        assert_eq!(slugify("/auth/verification-email/resend"), "authverification-emailresend");
        assert_eq!(slugify("Hello World"), "hello-world");
        assert_eq!(slugify("A.B.C"), "abc");  // Periods removed
        assert_eq!(slugify("日本語テスト"), "日本語テスト");  // Japanese preserved
        assert_eq!(slugify("test_underscore"), "test_underscore");  // Underscores preserved
        assert_eq!(slugify("a--b"), "a-b");  // Multiple hyphens collapsed
    }
}

#[test]
fn test_footnote_in_table() {
    let md = r#"| Col1 | Col2 | Col3 |
|------|------|------|
| [A][^1] | data | end |

[A]: #link
[^1]: Footnote one
"#;
    let html = render_markdown(md);
    println!("HTML: {}", html);
    // Check that table cells are separate
    assert!(html.contains("<td>data</td>") || html.contains(">data<"), "data should be in its own cell: {}", html);
}

#[test]
fn test_footnote_with_list() {
    let content = "- データソース項目の値\n- 上記以外の場合";
    let html = render_footnote_continuation(content, false);
    println!("Footnote continuation HTML: {}", html);
    assert!(html.contains("<li>") && html.contains("<ul>"), "Should contain list: {}", html);
}