PDF Processing Guide

from reportlab.platypus import Paragraph
from reportlab.lib.styles import ParagraphStyle
from reportlab.lib.enums import TA_LEFT, TA_CENTER

body_style = enbody_style = ParagraphStyle(
    name="ENBodyStyle",
    fontName="Times New Roman",  
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
header_style = ParagraphStyle(
    name='CoverTitle',
    fontName='Times New Roman',  
    fontSize=42,
    leading=50,
    alignment=TA_CENTER,
    spaceAfter=36
)

# Superscript: area unit
Paragraph('Total area: 500 m<super>2</super>', body_style)

# Subscript: chemical formula
Paragraph('The reaction produces CO<sub>2</sub> and H<sub>2</sub>O', body_style)

# Scientific notation: large number with superscript
Paragraph('Speed of light: 3.0 × 10<super>8</super> m/s', body_style)

# Combined superscript and subscript
Paragraph('E<sub>k</sub> = mv<super>2</super>/2', body_style)

# Bold heading
Paragraph('<b>Chapter 1: Introduction</b>', header_style)

# Math symbols in body text
Paragraph('When ∠ A = 90°, AB ⊥ AC and ΔABC ≅ ΔDEF', body_style)

from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
from reportlab.pdfbase.pdfmetrics import registerFontFamily

# Chinese fonts
pdfmetrics.registerFont(TTFont('Microsoft YaHei', '/usr/share/fonts/truetype/chinese/msyh.ttf'))
pdfmetrics.registerFont(TTFont('SimHei', '/usr/share/fonts/truetype/chinese/SimHei.ttf'))
pdfmetrics.registerFont(TTFont("SarasaMonoSC", '/usr/share/fonts/truetype/chinese/SarasaMonoSC-Regular.ttf'))

# English fonts
pdfmetrics.registerFont(TTFont('Times New Roman', '/usr/share/fonts/truetype/english/Times-New-Roman.ttf'))
pdfmetrics.registerFont(TTFont('Calibri', '/usr/share/fonts/truetype/english/calibri-regular.ttf'))

# Symbol/Formula font
pdfmetrics.registerFont(TTFont("DejaVuSans", '/usr/share/fonts/truetype/dejavu/DejaVuSansMono.ttf'))

# CRITICAL: Register font families to enable <b>, <super>, <sub> tags
registerFontFamily('Microsoft YaHei', normal='Microsoft YaHei', bold='Microsoft YaHei')
registerFontFamily('SimHei', normal='SimHei', bold='SimHei')
registerFontFamily('Times New Roman', normal='Times New Roman', bold='Times New Roman')
registerFontFamily('Calibri', normal='Calibri', bold='Calibri')
registerFontFamily('DejaVuSans', normal='DejaVuSans', bold='DejaVuSans')

from reportlab.lib.styles import ParagraphStyle
from reportlab.platypus import Paragraph
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont

pdfmetrics.registerFont(TTFont('SimHei', '/usr/share/fonts/truetype/chinese/SimHei.ttf'))
pdfmetrics.registerFont(TTFont('Times New Roman', '/usr/share/fonts/truetype/english/Times-New-Roman.ttf'))

# Base font is English; wrap Chinese parts:
enbody_style = ParagraphStyle(
    name="ENBodyStyle",
    fontName="Times New Roman",  # Base font for English
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
# Wrap Chinese segments with <font> tag
story.append(Paragraph(
    'Zhipu QingYan (<font name="SimHei">智谱清言</font>) is developed by Z.ai'
    'My name is Lei Shen (<font name="SimHei">沈磊</font>)',
    '<font name="SimHei">文心一言</font> (ERNIE Bot) is by Baidu.',
    enbody_style
))

# Base font is Chinese; wrap English parts:
cnbody_style = ParagraphStyle(
    name="CNBodyStyle",
    fontName="SimHei",  # Base font for Chinese
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
# Wrap Chinese segments with <font> tag
story.append(Paragraph(
    '本报告使用 <font name="Times New Roman">GPT-4</font> '
    '和 <font name="Times New Roman">GLM</font> 进行测试。',
    cnbody_style
))

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

# Cover page styles
cover_title_style = ParagraphStyle(
    name='CoverTitle',
    fontName='Microsoft YaHei',  # or 'Times New Roman' for English
    fontSize=42,
    leading=50,
    alignment=TA_CENTER,
    spaceAfter=36
)

cover_subtitle_style = ParagraphStyle(
    name='CoverSubtitle',
    fontName='SimHei',  # or 'Times New Roman' for English
    fontSize=20,
    leading=28,
    alignment=TA_CENTER,
    spaceAfter=48
)

cover_author_style = ParagraphStyle(
    name='CoverAuthor',
    fontName='SimHei',  # or 'Times New Roman' for English
    fontSize=14,
    leading=22,
    alignment=TA_CENTER,
    spaceAfter=18
)

# Cover page construction
story.append(Spacer(1, 120))  # Push down from top
story.append(Paragraph("报告主标题", cover_title_style))
story.append(Spacer(1, 36))
story.append(Paragraph("副标题或说明文字", cover_subtitle_style))
story.append(Spacer(1, 48))
story.append(Paragraph("作者姓名", cover_author_style))
story.append(Paragraph("所属机构", cover_author_style))
story.append(Spacer(1, 60))
story.append(Paragraph("2025年2月", cover_author_style))
story.append(PageBreak())  # Always page break after cover

# Define standard colors for consistent table styling
TABLE_HEADER_COLOR = colors.HexColor('#1F4E79')  # Dark blue for header
TABLE_HEADER_TEXT = colors.white                  # White text for header
TABLE_ROW_EVEN = colors.white                     # White for even rows
TABLE_ROW_ODD = colors.HexColor('#F5F5F5')        # Light gray for odd rows

# 1) key point in Chinese: wordWrap="CJK"
tbl_center = ParagraphStyle(
    "tbl_center",
    fontName="SimHei",
    fontSize=9,
    leading=12,
    alignment=TA_CENTER,
    wordWrap="CJK",
)

# 2) ALL content MUST be wrapped in Paragraph - NO EXCEPTIONS for text
findings_data = []
for a, b, c in findings:
    findings_data.append([
        Paragraph(a, tbl_center),
        Paragraph(b, tbl_center),
        Paragraph(c, tbl_center),   # ALL content MUST be wrapped in Paragraph
    ])

findings_table = Table(findings_data, colWidths=[1.8*cm, 3*cm, 9*cm])

from reportlab.platypus import Table, TableStyle, Paragraph, Image
from reportlab.lib.styles import ParagraphStyle
from reportlab.lib import colors
from reportlab.lib.enums import TA_CENTER, TA_LEFT, TA_RIGHT, TA_JUSTIFY

# Define styles for table cells
header_style = ParagraphStyle(
    name='TableHeader',
    fontName='Times New Roman',
    fontSize=11,
    textColor=colors.white,
    alignment=TA_CENTER
)

cell_style = ParagraphStyle(
    name='TableCell',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_CENTER
)

cell_style_jus = ParagraphStyle(
    name='TableCellLeft',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_JUSTIFY
)

cell_style_right = ParagraphStyle(
    name='TableCellRight',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_RIGHT
)

# ✅ CORRECT: All text content wrapped in Paragraph()
data = [
    # Header row - bold text with Paragraph
    [
        Paragraph('<b>Parameter</b>', header_style),
        Paragraph('<b>Unit</b>', header_style),
        Paragraph('<b>Value</b>', header_style),
        Paragraph('<b>Note</b>', header_style)
    ],
    # Data rows - all text in Paragraph
    [
        Paragraph('Temperature', cell_style_jus),
        Paragraph('°C', cell_style),
        Paragraph('25.5', cell_style_jus),
        Paragraph('Ambient', cell_style)
    ],
    [
        Paragraph('Pressure', cell_style_jus),
        Paragraph('Pa', cell_style),
        Paragraph('1.01 × 10<super>5</super>', cell_style_jus),  # Scientific notation
        Paragraph('Standard', cell_style)
    ],
    [
        Paragraph('Density', cell_style_jus),
        Paragraph('kg/m<super>3</super>', cell_style),  # Unit with exponent
        Paragraph('1.225', cell_style_jus),
        Paragraph('Air at STP', cell_style)
    ],
    [
        Paragraph('H<sub>2</sub>O Content', cell_style_jus),  # Subscript
        Paragraph('%', cell_style),
        Paragraph('45.2', cell_style_jus),
        Paragraph('Relative humidity', cell_style)
    ]
]

# ❌ PROHIBITED: Plain strings - NEVER DO THIS
# data = [
#     ['<b>Parameter</b>', '<b>Unit</b>', '<b>Value</b>'],  # Bold won't work!
#     ['Pressure', 'Pa', '1.01 × 10<super>5</super>'],      # Superscript won't work!
# ]

# Create table
table = Table(data, colWidths=[120, 80, 100, 120])
table.setStyle(TableStyle([
    # Header styling
    ('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#1F4E79')),
    ('TEXTCOLOR', (0, 0), (-1, 0), colors.white),
    # Alternating row colors
    ('BACKGROUND', (0, 1), (-1, 1), colors.white),
    ('BACKGROUND', (0, 2), (-1, 2), colors.HexColor('#F5F5F5')),
    ('BACKGROUND', (0, 3), (-1, 3), colors.white),
    ('BACKGROUND', (0, 4), (-1, 4), colors.HexColor('#F5F5F5')),
    # Grid and alignment
    ('GRID', (0, 0), (-1, -1), 0.5, colors.grey),
    ('VALIGN', (0, 0), (-1, -1), 'MIDDLE'),
    ('LEFTPADDING', (0, 0), (-1, -1), 8),
    ('RIGHTPADDING', (0, 0), (-1, -1), 8),
    ('TOPPADDING', (0, 0), (-1, -1), 6),
    ('BOTTOMPADDING', (0, 0), (-1, -1), 6),
]))

# Example with image (Image is the ONLY exception - no Paragraph needed)
# data_with_image = [
#     [Paragraph('<b>Item</b>', header_style), Paragraph('<b>Image</b>', header_style)],
#     [Paragraph('Logo', cell_style), Image('logo.png', width=50, height=50)],  # Image directly, no Paragraph
# ]

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate
import os

# Extract filename without extension for metadata title
pdf_filename = "financial_report_2024.pdf"
title_for_metadata = os.path.splitext(pdf_filename)[0]  # "financial_report_2024"

doc = SimpleDocTemplate(
    pdf_filename,
    pagesize=letter,
    title=title_for_metadata,    # MUST: Match filename
    author='Z.ai',               # MUST: Set to "Z.ai"
    creator='Z.ai',              # MUST: Set to "Z.ai"
    subject='Annual financial analysis and performance metrics'  # SHOULD: Describe purpose
)

from pypdf import PdfReader, PdfWriter
import os

pdf_filename = "output.pdf"
title_for_metadata = os.path.splitext(os.path.basename(pdf_filename))[0]

reader = PdfReader("input.pdf")
writer = PdfWriter()

for page in reader.pages:
    writer.add_page(page)

# Set metadata: Title, Author, Creator are REQUIRED
writer.add_metadata({
    '/Title': title_for_metadata,  # MUST: Match filename
    '/Author': 'Z.ai',             # MUST: Set to "Z.ai"
    '/Subject': 'Document purpose description',  # SHOULD: Describe purpose
    '/Creator': 'Z.ai'             # MUST: Set to "Z.ai"
})

with open(pdf_filename, "wb") as output:
    writer.write(output)

doc.build(story)
print("PDF built")

python scripts/add_zai_metadata.py output.pdf

print("✓ PDF generated with Z.ai metadata")

from pypdf import PdfReader, PdfWriter

# Read a PDF
reader = PdfReader("document.pdf")
print(f"Pages: {len(reader.pages)}")

# Extract text
text = ""
for page in reader.pages:
    text += page.extract_text()

from pypdf import PdfWriter, PdfReader

writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)

with open("merged.pdf", "wb") as output:
    writer.write(output)

reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"page_{i+1}.pdf", "wb") as output:
        writer.write(output)

reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Title: {meta.title}")
print(f"Author: {meta.author}")
print(f"Subject: {meta.subject}")
print(f"Creator: {meta.creator}")

# Add metadata to a single PDF (in-place)
python scripts/add_zai_metadata.py document.pdf

# Add metadata with custom title
python scripts/add_zai_metadata.py report.pdf -t "Q4 Financial Analysis"

# Batch process multiple PDFs
python scripts/add_zai_metadata.py *.pdf

reader = PdfReader("input.pdf")
writer = PdfWriter()

page = reader.pages[0]
page.rotate(90)  # Rotate 90 degrees clockwise
writer.add_page(page)

with open("rotated.pdf", "wb") as output:
    writer.write(output)

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

with pdfplumber.open("document.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        tables = page.extract_tables()
        for j, table in enumerate(tables):
            print(f"Table {j+1} on page {i+1}:")
            for row in table:
                print(row)

Do you need auto-TOC?
├─ YES → Use TocDocTemplate + doc.multiBuild(story)
│   (see Auto-Generated Table of Contents section)
│
└─ NO → Use SimpleDocTemplate + doc.build(story)
    (basic documents, or with optional Cross-References)

# --- Register fonts and font family ---
pdfmetrics.registerFont(TTFont('Times New Roman', '/usr/share/fonts/truetype/english/Times-New-Roman.ttf'))

# CRITICAL: Must call registerFontFamily() to enable <b> and <i> tags
registerFontFamily('Times New Roman', normal='Times New Roman', bold='Times New Roman')

# --- Define styles ---
body_style = ParagraphStyle(
    name='BodyStyle',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_JUSTIFY,
)
bold_style = ParagraphStyle(
    name='BoldStyle',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_JUSTIFY,
)
header_style = ParagraphStyle(
    name='HeaderStyle',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.white,
    alignment=TA_JUSTIFY,
)

# --- Body text examples ---
# Bold title
title = Paragraph('<b>Scientific Formulas and Chemical Expressions</b>', bold_style)

# Math formula with superscript and mathematical symbol ×
math_text = Paragraph(
    'The Einstein mass-energy equivalence is expressed as E = mc<super>2</super>. '
    'In applied physics, the gravitational force is F = 6.674 × 10<super>-11</super> × '
    'm<sub>1</sub>m<sub>2</sub>/r<super>2</super>, '
    'and the quadratic formula solves a<super>2</super> + b<super>2</super> = c<super>2</super>.',
    body_style,
)

# Chemical expressions with subscript
chem_text = Paragraph(
    'The combustion of methane: CH<sub>4</sub> + 2O<sub>2</sub> '
    '= CO<sub>2</sub> + 2H<sub>2</sub>O. '
    'Sulfuric acid (H<sub>2</sub>SO<sub>4</sub>) reacts with sodium hydroxide to produce '
    'Na<sub>2</sub>SO<sub>4</sub> and water.',
    body_style,
)

# PROHIBITED: "K.G. Palepu" may break after "K.G."
text = Paragraph("Professors (K.G. Palepu) proposed...",style)

# RIGHT: Use non-breaking space (U+00A0) to prevent breaking
text = Paragraph("Professors (K.G.\u00A0Palepu) proposed...",style)

# RIGHT: Add wordWrap='CJK' for proper typography
styles.add(ParagraphStyle(
    name='BodyStyle',
    fontName='SimHei',
    fontSize=10.5,
    leading=18,
    alignment=TA_LEFT,
    wordWrap='CJK'  # Prevents orphaned punctuation
))

# PROHIBITED: Normal newline character does NOT create line breaks
text = Paragraph("Line 1\nLine 2\nLine 3", style)  # Will render as single line!

# RIGHT: Use <br/> tag for line breaks
text = Paragraph("Line 1<br/>Line 2<br/>Line 3", style)

# Alternative: Split into multiple Paragraph objects
story.append(Paragraph("Line 1", style))
story.append(Paragraph("Line 2", style))
story.append(Paragraph("Line 3", style))

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

# Add text
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")

# Add a line
c.line(100, height - 140, 400, height - 140)

# Save
c.save()

# ❌ PROHIBIT - DO NOT USE
toc_entries = [("1. Title", "5"), ("2. Section", "10")]
for entry, page in toc_entries:
    story.append(Paragraph(f"{entry} {'.'*50} {page}", style))

def add_heading(text, style, level=0):
    """Create heading with bookmark for auto-TOC"""
    p = Paragraph(text, style)
    p.bookmark_name = text
    p.bookmark_level = level
    p.bookmark_text = text
    return p

# Usage:
story.append(add_heading("1. Introduction", styles['Heading1'], 0))
story.append(Paragraph('Content...', styles['Normal']))

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, PageBreak, Spacer
from reportlab.platypus.tableofcontents import TableOfContents
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import inch

class TocDocTemplate(SimpleDocTemplate):
    def __init__(self, *args, **kwargs):
        SimpleDocTemplate.__init__(self, *args, **kwargs)

    def afterFlowable(self, flowable):
        """Capture TOC entries after each flowable is rendered"""
        if hasattr(flowable, 'bookmark_name'):
            level = getattr(flowable, 'bookmark_level', 0)
            text = getattr(flowable, 'bookmark_text', '')
            self.notify('TOCEntry', (level, text, self.page))

# Create document
doc = TocDocTemplate("document.pdf", pagesize=letter)
story = []
styles = getSampleStyleSheet()

# Create Table of Contents
toc = TableOfContents()
toc.levelStyles = [
    ParagraphStyle(name='TOCHeading1', fontSize=14, leftIndent=20,
                   fontName='Times New Roman'),
    ParagraphStyle(name='TOCHeading2', fontSize=12, leftIndent=40,
                   fontName='Times New Roman'),
]
story.append(Paragraph("<b>Table of Contents</b>", styles['Title']))
story.append(Spacer(1, 0.2*inch))
story.append(toc)
story.append(PageBreak())

# Helper function: Create heading with TOC bookmark
def add_heading(text, style, level=0):
    p = Paragraph(text, style)
    p.bookmark_name = text
    p.bookmark_level = level
    p.bookmark_text = text
    return p

# Chapter 1: Introduction
story.append(add_heading("Chapter 1: Introduction", styles['Heading1'], 0))
story.append(Paragraph("This is the introduction chapter with some example content.",
                       styles['Normal']))
story.append(Spacer(1, 0.2*inch))

story.append(add_heading("1.1 Background", styles['Heading2'], 1))
story.append(Paragraph("Background information goes here.", styles['Normal']))


# Chapter 2: Conclusion
story.append(add_heading("Chapter 2: Conclusion", styles['Heading1'], 0))
story.append(Paragraph("This concludes our document.", styles['Normal']))
story.append(Spacer(1, 0.2*inch))

story.append(add_heading("2.1 Summary", styles['Heading2'], 1))
story.append(Paragraph("Summary of the document.", styles['Normal']))

# Build the document (must use multiBuild for TOC to work)
doc.multiBuild(story)

print("PDF with Table of Contents created successfully!")

from reportlab.lib.pagesizes import letter
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.enums import TA_CENTER
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib import colors
from reportlab.platypus import Table, TableStyle


class CrossReferenceDocument:
    """Manages cross-references throughout the document"""

    def __init__(self):
        self.figures = {}
        self.tables = {}
        self.refs = {}
        self.figure_counter = 0
        self.table_counter = 0
        self.ref_counter = 0

    def add_figure(self, name):
        """Add a figure and return its number"""
        if name not in self.figures:
            self.figure_counter += 1
            self.figures[name] = self.figure_counter
        return self.figures[name]

    def add_table(self, name):
        """Add a table and return its number"""
        if name not in self.tables:
            self.table_counter += 1
            self.tables[name] = self.table_counter
        return self.tables[name]

    def add_reference(self, name):
        """Add a reference and return its number"""
        if name not in self.refs:
            self.ref_counter += 1
            self.refs[name] = self.ref_counter
        return self.refs[name]


def build_document():
    doc = SimpleDocTemplate("cross_ref.pdf", pagesize=letter)
    xref = CrossReferenceDocument()
    styles = getSampleStyleSheet()

    # Caption style
    styles.add(ParagraphStyle(
        name='Caption',
        parent=styles['Normal'],
        alignment=TA_CENTER,
        fontSize=10,
        textColor=colors.HexColor('#333333')
    ))

    story = []

    # Step 1: Register all figures, tables, and references FIRST
    fig1 = xref.add_figure('sample')
    table1 = xref.add_table('data')
    ref1 = xref.add_reference('author2024')

    # Step 2: Use them in text
    intro = f"""
    See Figure {fig1} for details and Table {table1} for data<sup>[{ref1}]</sup>.
    """
    story.append(Paragraph(intro, styles['Normal']))
    story.append(Spacer(1, 0.2*inch))

    # Step 3: Create figures and tables with numbered captions
    story.append(Paragraph(f"<b>Figure {fig1}.</b> Sample Figure Caption",
        styles['Caption']
    ))

    # Table example
    header_style = ParagraphStyle(
    name='TableHeader',
    fontName='Times New Roman',
    fontSize=11,
    textColor=colors.white,
    alignment=TA_CENTER
    )

    cell_style = ParagraphStyle(
        name='TableCell',
        fontName='Times New Roman',
        fontSize=10,
        textColor=colors.black,
        alignment=TA_CENTER
    )

    # All text content wrapped in Paragraph() 
    data = [
        [Paragraph('<b>Item</b>', header_style), Paragraph('<b>Value</b>', header_style)],
        [Paragraph('A', cell_style), Paragraph('10', cell_style)],
        [Paragraph('B', cell_style), Paragraph('20', cell_style)],
    ]
    t = Table(data, colWidths=[2*inch, 2*inch])
    t.setStyle(TableStyle([
        ('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#1F4E79')),
        ('TEXTCOLOR', (0, 0), (-1, 0), colors.white),
        ('ALIGN', (0, 0), (-1, -1), 'CENTER'),
        ('GRID', (0, 0), (-1, -1), 0.5, colors.grey),
    ]))
    story.append(t)
    story.append(Spacer(1, 6))
    story.append(Paragraph(f"<b>Table {table1}.</b> Sample Data Table",
        styles['Caption']
    ))

    story.append(PageBreak())

    # Step 4: Reference again in discussion
    discussion = f"""
    As shown in Figure {fig1} and Table {table1}, results are clear<sup>[{ref1}]</sup>.
    """
    story.append(Paragraph(discussion, styles['Normal']))

    # Step 5: Bibliography section
    story.append(PageBreak())
    story.append(Paragraph("<b>References</b>", styles['Heading1']))
    story.append(Paragraph(
        f"[{ref1}] Author, A. (2024). Example Reference. <i>Journal Name</i>.",
        styles['Normal']
    ))

    doc.build(story)
    print("PDF with cross-references created!")


if __name__ == '__main__':
    build_document()

# Extract text
pdftotext input.pdf output.txt

# Extract text preserving layout
pdftotext -layout input.pdf output.txt

# Extract specific pages
pdftotext -f 1 -l 5 input.pdf output.txt  # Pages 1-5

# Merge PDFs
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

# Split pages
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf

# Rotate pages
qpdf input.pdf output.pdf --rotate=+90:1  # Rotate page 1 by 90 degrees

# Remove password
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

# Add metadata to a single PDF (in-place)
python scripts/add_zai_metadata.py document.pdf

# Add metadata to a single PDF (create new file)
python scripts/add_zai_metadata.py input.pdf -o output.pdf

# Add metadata with custom title
python scripts/add_zai_metadata.py report.pdf -t "Q4 Financial Analysis"

# Batch process all PDFs in current directory
python scripts/add_zai_metadata.py *.pdf

# Quiet mode (no output)
python scripts/add_zai_metadata.py document.pdf -q

# Show help
python scripts/add_zai_metadata.py --help

# Requires: pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path

# Convert PDF to images
images = convert_from_path('scanned.pdf')

# OCR each page
text = ""
for i, image in enumerate(images):
    text += f"Page {i+1}:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)

from pypdf import PdfReader, PdfWriter

# Create watermark (or load existing)
watermark = PdfReader("watermark.pdf").pages[0]

# Apply to all pages
reader = PdfReader("document.pdf")
writer = PdfWriter()

for page in reader.pages:
    page.merge_page(watermark)
    writer.add_page(page)

with open("watermarked.pdf", "wb") as output:
    writer.write(output)

from pypdf import PdfReader, PdfWriter

reader = PdfReader("input.pdf")
writer = PdfWriter()

for page in reader.pages:
    writer.add_page(page)

# Add password
writer.encrypt("userpassword", "ownerpassword")

with open("encrypted.pdf", "wb") as output:
    writer.write(output)

from reportlab.lib.styles import ParagraphStyle
from reportlab.platypus import Paragraph
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont

pdfmetrics.registerFont(TTFont('SimHei', '/usr/share/fonts/truetype/chinese/SimHei.ttf'))
pdfmetrics.registerFont(TTFont('Times New Roman', '/usr/share/fonts/truetype/english/Times-New-Roman.ttf'))

# Base font is English; wrap Chinese parts:
enbody_style = ParagraphStyle(
    name="ENBodyStyle",
    fontName="Times New Roman",  # Base font for English
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
# Wrap Chinese segments with <font> tag
story.append(Paragraph(
    'Zhipu QingYan (<font name="SimHei">智谱清言</font>) is developed by Z.ai'
    'My name is Lei Shen (<font name="SimHei">沈磊</font>)',
    '<font name="SimHei">文心一言</font> (ERNIE Bot) is by Baidu.',
    enbody_style
))

# Base font is Chinese; wrap English parts:
cnbody_style = ParagraphStyle(
    name="CNBodyStyle",
    fontName="SimHei",  # Base font for Chinese
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
# Wrap Chinese segments with <font> tag
story.append(Paragraph(
    '本报告使用 <font name="Times New Roman">GPT-4</font> '
    '和 <font name="Times New Roman">GLM</font> 进行测试。',
    cnbody_style
))

sms3 = \\\"\\\"\\\"Hi [FIRST_NAME] 
You're invited! Join us for an exclusive first look at the Carolina Herrera Resort 2025 collection—before it opens to the public.
[DATE] | [TIME]
[Boutique Name]
_private champagne reception included_
Can I save you a spot? Just let me know!
[Your Name]\\\"\\\"\\\"
sms3_box = Table([[Paragraph(sms3, sms1_style)]], colWidths=[400])

# IMPORTANT:
# Paragraph does NOT treat '\n' as a line break.
# Use <br/> to force line breaks.
sms3 = """Hi [FIRST_NAME]<br/><br/>
You're invited! Join us for an exclusive first look at the Carolina Herrera Resort 2025 collection—before it opens to the public.<br/><br/>
[DATE] | [TIME]<br/>
[Boutique Name]<br/><br/>
<i>private champagne reception included</i><br/><br/>
Can I save you a spot? Just let me know!<br/><br/>
[Your Name]"""
sms3_box = Table([[Paragraph(sms3, sms1_style)]], colWidths=[400])

# NEVER DO THIS - formatting will NOT work
data = [
    ['<b>Header</b>', 'Value'],           # Bold won't render
    ['Temperature', '25°C'],               # No style control
    ['Pressure', '1.01 × 10<super>5</super>'],  # Superscript won't work
]

# ALWAYS DO THIS
data = [
    [Paragraph('<b>Header</b>', header_style), Paragraph('Value', header_style)],
    [Paragraph('Temperature', cell_style), Paragraph('25°C', cell_style)],
    [Paragraph('Pressure', cell_style), Paragraph('1.01 × 10<super>5</super>', cell_style)],
]

from PIL import Image as PILImage
from reportlab.platypus import Image
# Get original dimensions
pil_img = PILImage.open('image.png')
orig_w, orig_h = pil_img.size
# Scale to fit width while preserving aspect ratio
target_width = 400
scale = target_width / orig_w
img = Image('image.png', width=target_width, height=orig_h * scale)

scripts/sanitize_code.py

# Step 1: ALWAYS write code to a .py file first
cat > generate_pdf.py << 'PYEOF'
# ... your PDF generation code here ...
PYEOF

# Step 2: Sanitize forbidden characters (MUST run before execution)
python scripts/sanitize_code.py generate_pdf.py

# Step 3: Execute the sanitized code
python generate_pdf.py

# ❌ PROHIBITED: python -c with inline code (cannot be sanitized)
python -c "from reportlab... doc.build(story)"

# ❌ PROHIBITED: heredoc without saving to file first (cannot be sanitized)
python3 << 'EOF'
from reportlab...
EOF

# ❌ PROHIBITED: executing the .py file WITHOUT sanitizing first
python generate_pdf.py  # Missing sanitization step!

# 1. Write to file  →  2. Sanitize  →  3. Execute
cat > generate_pdf.py << 'PYEOF'
...code...
PYEOF
python scripts/sanitize_code.py generate_pdf.py
python generate_pdf.py