gdoc updater replace patterns

replace_patterns.py

def replace_patterns(content):
    requests = []

    patterns_and_replacements = [
        # Pattern 1: Replace underscores with hyphens in filenames
        (
            re.compile(r'''
                \[image:     # Literal "[image:"
                \s*          # Zero or more whitespace characters
                (            # Start of capturing group
                [a-zA-Z0-9_]+  # One or more alphanumeric characters or underscores
                )            # End of capturing group
                \]           # Literal closing square bracket
            ''', re.VERBOSE),
            
            lambda m: f'[image: {m.group(1).replace("_", "-")}]'
            # Replace underscores with hyphens in the captured filename
        ),
        
        # Pattern 2: Remove aws-start-n- from the filename, but keep the rest
        (
            re.compile(r'''
                \[image:     # Literal "[image:"
                \s*          # Zero or more whitespace characters
                aws-start-   # Literal "aws-start-"
                \d+          # One or more digits
                -            # Literal hyphen
                (            # Start of capturing group
                .+           # One or more of any character (except newline)
                )            # End of capturing group
                \]           # Literal closing square bracket
            ''', re.VERBOSE),
            
            lambda m: f'[image: {m.group(1)}]'
            # Keep only the part after "aws-start-n-"
        ),
    ]    
    
    for item in content:
        if 'paragraph' in item:
            for element in item['paragraph']['elements']:
                if 'textRun' in element:
                    text = element['textRun']['content']
                    original_text = text
                    
                    for pattern, replacement in patterns_and_replacements:
                        text = re.sub(pattern, replacement, text)
                    
                    if text != original_text:
                        requests.append({
                            'replaceAllText': {
                                'containsText': {
                                    'text': original_text,
                                    'matchCase': True,
                                },
                                'replaceText': text,
                            }
                        })
    return requests