Leyenda

apply_content.py

@@ -4,23 +4,25 @@
 import re
 import os
 import shutil
-from bs4 import BeautifulSoup, NavigableString
-from latex2mathml.converter import convert as latex_to_mathml
-from PIL import Image
-
-BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-TEMPLATE_INPUT = os.path.join(BASE_DIR, 'instructions/plantilla_individual.htm')
-TEMPLATE_OUTPUT = os.path.join(BASE_DIR, 'thesis_output/plantilla_individual.htm')
-DOCS_DIR = os.path.join(BASE_DIR, 'docs')
-
-# Accept Fuente/Source lines with or without markdown bold
-SOURCE_LINE_RE = re.compile(r'^\s*(?:\*{1,2})?(Fuente|Source):(?:\*{1,2})?\s*(.*)$', re.IGNORECASE)
-
-# Global counters for tables and figures
-table_counter = 0
-figure_counter = 0
-anexo_table_counter = 0
-anexo_figure_counter = 0
+from bs4 import BeautifulSoup, NavigableString
+from latex2mathml.converter import convert as latex_to_mathml
+from PIL import Image
+
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+TEMPLATE_INPUT = os.path.join(BASE_DIR, 'instructions/plantilla_individual.htm')
+TEMPLATE_OUTPUT = os.path.join(BASE_DIR, 'thesis_output/plantilla_individual.htm')
+DOCS_DIR = os.path.join(BASE_DIR, 'docs')
+
+# Accept Fuente/Source lines with or without markdown bold
+SOURCE_LINE_RE = re.compile(r'^\s*(?:\*{1,2})?(Fuente|Source):(?:\*{1,2})?\s*(.*)$', re.IGNORECASE)
+# Accept Leyenda lines with or without markdown bold
+LEYENDA_LINE_RE = re.compile(r'^\s*(?:\*{1,2})?Leyenda:(?:\*{1,2})?\s*(.*)$', re.IGNORECASE)
+
+# Global counters for tables and figures
+table_counter = 0
+figure_counter = 0
+anexo_table_counter = 0
+anexo_figure_counter = 0
 # Global sequential counter for figure filenames (figura_1.png, figura_2.png, etc.)
 global_figure_index = 0
 
@@ -48,7 +50,7 @@ def md_to_html_para(text):
     text = re.sub(r'\[([^\]]+)\]\(([^)]+)\)', r'<a href="\2">\1</a>', text)
     return text
 
-def convert_latex_formulas(text):
+def convert_latex_formulas(text):
     """Convert LaTeX formulas to MathML for Word compatibility."""
     # Block formulas $$...$$
     def convert_block(match):
@@ -69,22 +71,33 @@ def convert_latex_formulas(text):
         except:
             return match.group(0)
 
-    text = re.sub(r'\$([^$]+)\$', convert_inline, text)
-    return text
-
-def extract_source_from_line(line):
-    """Return source text if line is a Fuente/Source line, otherwise None."""
-    match = SOURCE_LINE_RE.match(line.strip())
-    if not match:
-        return None
-    return match.group(2).strip()
-
-def is_source_line(line):
-    """Check whether a line starts with Fuente:/Source: (optionally bold)."""
-    return SOURCE_LINE_RE.match(line.strip()) is not None
-
-def extract_table_title(lines, current_index):
-    """Look for table title in preceding lines (e.g., **Tabla 1.** *Title*)."""
+    text = re.sub(r'\$([^$]+)\$', convert_inline, text)
+    return text
+
+def extract_source_from_line(line):
+    """Return source text if line is a Fuente/Source line, otherwise None."""
+    match = SOURCE_LINE_RE.match(line.strip())
+    if not match:
+        return None
+    return match.group(2).strip()
+
+def is_source_line(line):
+    """Check whether a line starts with Fuente:/Source: (optionally bold)."""
+    return SOURCE_LINE_RE.match(line.strip()) is not None
+
+def extract_leyenda_from_line(line):
+    """Return leyenda text if line is a Leyenda line, otherwise None."""
+    match = LEYENDA_LINE_RE.match(line.strip())
+    if not match:
+        return None
+    return match.group(1).strip()
+
+def is_leyenda_line(line):
+    """Check whether a line starts with Leyenda: (optionally bold)."""
+    return LEYENDA_LINE_RE.match(line.strip()) is not None
+
+def extract_table_title(lines, current_index):
+    """Look for table title in preceding lines (e.g., **Tabla 1.** *Title*)."""
     # Check previous non-empty lines for table title
     for i in range(current_index - 1, max(0, current_index - 5), -1):
         line = lines[i].strip()
@@ -172,8 +185,11 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
             bookmark_id = f"_Ref_Fig{fig_num}"
             # mso-pagination:keep-with-next ensures caption stays with figure image (correct MSO property)
             # For Anexo figures, use static text (no SEQ field) to prevent Word from overwriting A1, A2...
+            # Add TC field so Anexo figures appear in Table of Figures index
+            # Use \f c to match the TOC field identifier in the template
             if is_anexo:
-                html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption style="text-align:center;mso-pagination:keep-with-next"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Figura {fig_num}.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%">{fig_title}</span></i></p>''')
+                tc_field = f'''<!--[if supportFields]><span style='mso-element:field-begin'></span> TC "Figura {fig_num}. {fig_title}" \\f c \\l 1 <span style='mso-element:field-end'></span><![endif]-->'''
+                html_blocks.append(f'''<a name="{bookmark_id}"></a>{tc_field}<p class=MsoCaption style="text-align:center;mso-pagination:keep-with-next"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Figura {fig_num}.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%">{fig_title}</span></i></p>''')
             else:
                 html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption style="text-align:center;mso-pagination:keep-with-next"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Figura <!--[if supportFields]><span style='mso-element:field-begin'></span> SEQ Figura \\* ARABIC <span style='mso-element:field-separator'></span><![endif]-->{fig_num}<!--[if supportFields]><span style='mso-element:field-end'></span><![endif]-->.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%">{fig_title}</span></i></p>''')
 
@@ -204,19 +220,27 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
 
             # Check if next non-empty line has custom Fuente
             custom_source = None
+            fig_leyenda = None
             lookahead = i + 1
             while lookahead < len(lines) and not lines[lookahead].strip():
                 lookahead += 1
-            if lookahead < len(lines):
-                next_line = lines[lookahead].strip()
-                if is_source_line(next_line):
-                    # Extract custom source, removing markdown formatting
-                    custom_source = extract_source_from_line(next_line)
-                    # Ensure it ends with a period
-                    if custom_source and not custom_source.endswith('.'):
-                        custom_source += '.'
-                    # Skip this line by advancing i past it
-                    i = lookahead
+            if lookahead < len(lines):
+                next_line = lines[lookahead].strip()
+                if is_source_line(next_line):
+                    # Extract custom source, removing markdown formatting
+                    custom_source = extract_source_from_line(next_line)
+                    # Ensure it ends with a period
+                    if custom_source and not custom_source.endswith('.'):
+                        custom_source += '.'
+                    # Skip this line by advancing i past it
+                    i = lookahead
+                    # Check for Leyenda after source
+                    leyenda_idx = i + 1
+                    while leyenda_idx < len(lines) and not lines[leyenda_idx].strip():
+                        leyenda_idx += 1
+                    if leyenda_idx < len(lines) and is_leyenda_line(lines[leyenda_idx]):
+                        fig_leyenda = extract_leyenda_from_line(lines[leyenda_idx])
+                        i = leyenda_idx
 
             if custom_source:
                 source_html = md_to_html_para(custom_source)
@@ -224,6 +248,13 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
             else:
                 html_blocks.append(f'''<p class=Piedefoto-tabla style="margin-left:0cm;text-align:center"><span lang=ES>Fuente: Elaboración propia.</span></p>''')
 
+            # Add leyenda if present (same style as Fuente, new line)
+            if fig_leyenda:
+                leyenda_html = md_to_html_para(fig_leyenda)
+                if not fig_leyenda.endswith('.'):
+                    leyenda_html += '.'
+                html_blocks.append(f'''<p class=Piedefoto-tabla style="margin-left:0cm;text-align:center"><span lang=ES>Leyenda: {leyenda_html}</span></p>''')
+
             html_blocks.append('<p class=MsoNormal><span lang=ES><o:p>&nbsp;</o:p></span></p>')
             i += 1
             continue
@@ -249,7 +280,7 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
         if line.startswith('####'):
             text = line.lstrip('#').strip()
             # Apply consistent styling like h2/h3, disable numbering for h4
-            html_blocks.append(f'<h4 style="mso-list:none"><span lang=ES style="text-transform:none">{text}</span></h4>')
+            html_blocks.append(f'<h4 style="mso-list:none"><b><span lang=ES style="text-transform:none">{text}</span></b></h4>')
             i += 1
             continue
         elif line.startswith('###'):
@@ -314,11 +345,19 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
 
             # Look ahead for source (skip blank lines first)
             source_idx = i
-            while source_idx < len(lines) and not lines[source_idx].strip():
-                source_idx += 1
-            if source_idx < len(lines) and is_source_line(lines[source_idx]):
-                table_source = extract_source_from_line(lines[source_idx])
-                i = source_idx + 1
+            table_leyenda = None
+            while source_idx < len(lines) and not lines[source_idx].strip():
+                source_idx += 1
+            if source_idx < len(lines) and is_source_line(lines[source_idx]):
+                table_source = extract_source_from_line(lines[source_idx])
+                i = source_idx + 1
+                # Check for Leyenda after source (skip blank lines)
+                leyenda_idx = i
+                while leyenda_idx < len(lines) and not lines[leyenda_idx].strip():
+                    leyenda_idx += 1
+                if leyenda_idx < len(lines) and is_leyenda_line(lines[leyenda_idx]):
+                    table_leyenda = extract_leyenda_from_line(lines[leyenda_idx])
+                    i = leyenda_idx + 1
 
             # Add table title with MsoCaption class and proper Word SEQ field for cross-reference
             # Format: "Tabla X." in bold, title in italic (per UNIR guidelines)
@@ -334,8 +373,11 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
                 clean_title = "Tabla de datos."
             # mso-pagination:keep-with-next ensures caption stays with table (correct MSO property)
             # For Anexo tables, use static text (no SEQ field) to prevent Word from overwriting A1, A2...
+            # Add TC field so Anexo tables appear in Table of Tables index
+            # Use \f t identifier - template TOC field will be modified to include this
             if is_anexo:
-                html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption style="mso-pagination:keep-with-next"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Tabla {table_num}.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%">{clean_title}</span></i></p>''')
+                tc_field = f'''<!--[if supportFields]><span style='mso-element:field-begin'></span> TC "Tabla {table_num}. {clean_title}" \\f t \\l 1 <span style='mso-element:field-end'></span><![endif]-->'''
+                html_blocks.append(f'''<a name="{bookmark_id}"></a>{tc_field}<p class=MsoCaption style="mso-pagination:keep-with-next"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Tabla {table_num}.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%">{clean_title}</span></i></p>''')
             else:
                 html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption style="mso-pagination:keep-with-next"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Tabla <!--[if supportFields]><span style='mso-element:field-begin'></span> SEQ Tabla \\* ARABIC <span style='mso-element:field-separator'></span><![endif]-->{table_num}<!--[if supportFields]><span style='mso-element:field-end'></span><![endif]-->.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%">{clean_title}</span></i></p>''')
 
@@ -363,6 +405,14 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
             if not table_source.endswith('.'):
                 source_html += '.'
             html_blocks.append(f'<p class=Piedefoto-tabla style="margin-left:0cm"><span lang=ES>Fuente: {source_html}</span></p>')
+
+            # Add leyenda if present (same style as Fuente, new line)
+            if table_leyenda:
+                leyenda_html = md_to_html_para(table_leyenda)
+                if not table_leyenda.endswith('.'):
+                    leyenda_html += '.'
+                html_blocks.append(f'<p class=Piedefoto-tabla style="margin-left:0cm"><span lang=ES>Leyenda: {leyenda_html}</span></p>')
+
             html_blocks.append('<p class=MsoNormal><span lang=ES><o:p>&nbsp;</o:p></span></p>')
             continue
 
@@ -376,24 +426,63 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
             html_blocks.append(f'<p class=MsoQuote><i><span lang=ES>{md_to_html_para(quote_text)}</span></i></p>')
             continue
 
-        # Bullet list
+        # Bullet list (handle blank lines between items)
         if re.match(r'^[\-\*\+]\s', line):
-            while i < len(lines) and re.match(r'^[\-\*\+]\s', lines[i]):
-                item_text = lines[i][2:].strip()
-                item_text = convert_latex_formulas(item_text)
-                html_blocks.append(f'<p class=MsoListParagraphCxSpMiddle style="margin-left:36pt;text-indent:-18pt"><span lang=ES style="font-family:Symbol">·</span><span lang=ES style="font-size:7pt">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</span><span lang=ES>{md_to_html_para(item_text)}</span></p>')
-                i += 1
+            # Collect all bullet items first
+            bullet_items = []
+            while i < len(lines):
+                # Skip blank lines
+                while i < len(lines) and not lines[i].strip():
+                    i += 1
+                # Check if next non-blank line is a bullet item
+                if i < len(lines) and re.match(r'^[\-\*\+]\s', lines[i]):
+                    item_text = lines[i][2:].strip()
+                    item_text = convert_latex_formulas(item_text)
+                    bullet_items.append(md_to_html_para(item_text))
+                    i += 1
+                else:
+                    break
+            # Output with proper First/Middle/Last classes
+            for idx, item in enumerate(bullet_items):
+                if len(bullet_items) == 1:
+                    cls = 'MsoListParagraph'
+                elif idx == 0:
+                    cls = 'MsoListParagraphCxSpFirst'
+                elif idx == len(bullet_items) - 1:
+                    cls = 'MsoListParagraphCxSpLast'
+                else:
+                    cls = 'MsoListParagraphCxSpMiddle'
+                html_blocks.append(f'<p class={cls} style="margin-left:36pt;text-indent:-18pt"><span lang=ES style="font-family:Symbol">·</span><span lang=ES style="font-size:7pt">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</span><span lang=ES>{item}</span></p>')
             continue
 
-        # Numbered list
+        # Numbered list (handle blank lines between items)
         if re.match(r'^\d+\.\s', line):
-            num = 1
-            while i < len(lines) and re.match(r'^\d+\.\s', lines[i]):
-                item_text = re.sub(r'^\d+\.\s*', '', lines[i]).strip()
-                item_text = convert_latex_formulas(item_text)
-                html_blocks.append(f'<p class=MsoListParagraphCxSpMiddle style="margin-left:36pt;text-indent:-18pt"><span lang=ES>{num}.<span style="font-size:7pt">&nbsp;&nbsp;&nbsp;</span>{md_to_html_para(item_text)}</span></p>')
-                num += 1
-                i += 1
+            # Collect all numbered items first
+            numbered_items = []
+            while i < len(lines):
+                # Skip blank lines
+                while i < len(lines) and not lines[i].strip():
+                    i += 1
+                # Check if next non-blank line is a numbered item
+                if i < len(lines) and re.match(r'^\d+\.\s', lines[i]):
+                    item_text = re.sub(r'^\d+\.\s*', '', lines[i]).strip()
+                    item_text = convert_latex_formulas(item_text)
+                    numbered_items.append(md_to_html_para(item_text))
+                    i += 1
+                else:
+                    break
+            # Output with proper First/Middle/Last classes
+            for idx, item in enumerate(numbered_items):
+                num = idx + 1
+                if len(numbered_items) == 1:
+                    cls = 'MsoListParagraph'
+                elif idx == 0:
+                    cls = 'MsoListParagraphCxSpFirst'
+                elif idx == len(numbered_items) - 1:
+                    cls = 'MsoListParagraphCxSpLast'
+                else:
+                    cls = 'MsoListParagraphCxSpMiddle'
+                html_blocks.append(f'<p class={cls} style="margin-left:36pt;text-indent:-18pt"><span lang=ES>{num}.<span style="font-size:7pt">&nbsp;&nbsp;&nbsp;</span>{item}</span></p>')
             continue
 
         # Skip lines that are just table/figure titles (they'll be handled with the table/figure)
@@ -403,9 +492,12 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
         if line.strip().startswith('**Figura') or line.strip().startswith('*Figura'):
             i += 1
             continue
-        if is_source_line(line):
-            i += 1
-            continue
+        if is_source_line(line):
+            i += 1
+            continue
+        if is_leyenda_line(line):
+            i += 1
+            continue
 
         # Regular paragraph
         para_lines = [line]
@@ -523,6 +615,17 @@ def main():
 
     print("Reading template...")
     html_content = read_file(TEMPLATE_INPUT)
+
+    # Modify the Table of Tables TOC field to include TC entries with \f t identifier
+    # Original: TOC \h \z \t "Tablas;1" \c "Tabla"
+    # Modified: TOC \f t \h \z \t "Tablas;1" \c "Tabla"
+    # Use regex to handle whitespace/HTML variations in the TOC field
+    html_content = re.sub(
+        r'(TOC\s+)(\\h\s+\\z\s+\\t\s*\n?\s*&quot;Tablas;1&quot;)',
+        r'\1\\f t \2',
+        html_content
+    )
+
     soup = BeautifulSoup(html_content, 'html.parser')
 
     print("Reading docs content...")
@@ -671,10 +774,10 @@ def main():
             # Also remove surrounding caption and source
             prev_sib = table.find_previous_sibling()
             next_sib = table.find_next_sibling()
-            if prev_sib and 'Tabla 1. Ejemplo' in prev_sib.get_text():
-                prev_sib.decompose()
-            if next_sib and SOURCE_LINE_RE.search(next_sib.get_text().strip()):
-                next_sib.decompose()
+            if prev_sib and 'Tabla 1. Ejemplo' in prev_sib.get_text():
+                prev_sib.decompose()
+            if next_sib and SOURCE_LINE_RE.search(next_sib.get_text().strip()):
+                next_sib.decompose()
             table.decompose()
             print("    ✓ Removed template table example")
             break