Function clean_extracted_text

skills/pdf-parser/scripts/parse_pdf.py:141–167

Normalize PDF text so downstream regexes behave predictably.

(text: str)

def clean_extracted_text(text: str) -> str:
    """Normalize PDF text so downstream regexes behave predictably."""
    if not text:
        return ""

    text = (
        text.replace("\r\n", "\n")
        .replace("\r", "\n")
        .replace("\u200b", "")
        .replace("\u200c", "")
        .replace("\u200d", "")
        .replace("\ufeff", "")
    )

    cleaned_lines: List[str] = []
    previous_blank = False
    for raw_line in text.split("\n"):
        line = re.sub(r"[ \t]+", " ", raw_line).strip()
        if not line:
            if not previous_blank:
                cleaned_lines.append("")
            previous_blank = True
            continue
        cleaned_lines.append(line)
        previous_blank = False

    return "\n".join(cleaned_lines).strip()


def _normalize_heading_line(line: str) -> str: