striprtf

from striprtf.striprtf import rtf_to_text

from striprtf.striprtf import rtf_to_text, remove_pict_groups

from striprtf import __version__

from striprtf.striprtf import rtf_to_text

# Convert RTF string to plain text
rtf = "some RTF encoded string"
text = rtf_to_text(rtf)
print(text)

# With custom encoding
rtf = "some RTF encoded string in latin1"  
text = rtf_to_text(rtf, encoding="latin-1")
print(text)

# With error handling for problematic encodings
rtf = "some RTF encoded string"
text = rtf_to_text(rtf, errors="ignore")
print(text)

def rtf_to_text(text, encoding="cp1252", errors="strict"):
    """
    Converts RTF text to plain text.

    Parameters:
    - text (str): The RTF text to convert
    - encoding (str): Input encoding, defaults to "cp1252". Ignored if RTF file contains explicit codepage directive
    - errors (str): How to handle encoding errors. "strict" (default) raises errors, "ignore" skips problematic characters

    Returns:
    str: The converted RTF text as a Python unicode string
    
    Raises:
    UnicodeDecodeError: When encoding errors occur and errors="strict"
    """

def remove_pict_groups(rtf_text):
    """
    Remove all \\pict groups with binary data from the RTF text.
    
    Parameters:
    - rtf_text (str): The RTF text containing potentially problematic \\pict groups
    
    Returns:
    str: The RTF text with binary-encoded \\pict groups removed
    
    Note: Returns original text if no binary-encoded \\pict groups are found
    """

def main():
    """
    Command-line entry point for converting RTF files to text.
    Located in striprtf/striprtf script file.
    
    Usage: striprtf <rtf_file>
    
    Arguments:
    - rtf_file: Path to RTF file to convert (required, file opened with UTF-8 encoding)
    
    Options:  
    - --version: Show version and exit
    
    Note: Installed as 'striprtf' command via package scripts configuration
    """

charset_map: dict
# Mapping of RTF charset numbers to Python encoding names
# Contains mappings for major character sets including cp1252, cp932, cp949, etc.

destinations: frozenset  
# Set of RTF control words that specify "destinations" to ignore during parsing
# Contains RTF keywords like 'fonttbl', 'colortbl', 'stylesheet', etc.

specialchars: dict
# Translation mapping for special RTF characters to Unicode equivalents  
# Maps RTF escape sequences to actual characters (e.g., 'emdash' -> '\\u2014')

sectionchars: dict
# Translation mapping for RTF section and paragraph control words
# Maps section-related RTF keywords to line break characters (e.g., 'par' -> '\\n')

PATTERN: re.Pattern
# Main regex pattern for parsing RTF tokens and control words

HYPERLINKS: re.Pattern  
# Regex pattern for extracting hyperlinks from RTF HYPERLINK fields

FONTTABLE: re.Pattern
# Regex pattern for parsing font table information

from striprtf.striprtf import rtf_to_text

# Read RTF file and convert to text
with open('document.rtf', 'r', encoding='utf-8') as f:
    rtf_content = f.read()

plain_text = rtf_to_text(rtf_content)
print(plain_text)

from striprtf.striprtf import rtf_to_text

# For problematic RTF files with encoding issues
try:
    text = rtf_to_text(rtf_content, encoding="cp1252", errors="strict")
except UnicodeDecodeError:
    # Fallback to ignore encoding errors
    text = rtf_to_text(rtf_content, errors="ignore")

from striprtf.striprtf import rtf_to_text, remove_pict_groups

# For RTF files with known binary picture issues, preprocess first
rtf_content = "\\rtf1\\pict\\bin1024{binary data here}\\par text"
cleaned_rtf = remove_pict_groups(rtf_content)
text = rtf_to_text(cleaned_rtf)

# Convert RTF file to plain text
striprtf document.rtf

# Check version
striprtf --version