"""CV text cleanup helpers for the PDF extractor.

Pure module: no FastAPI imports and no HTTPException.

Designer-made resumes position every glyph individually, so pypdf hands back
"S K I L L S" instead of "SKILLS". In that layout a single space is glyph
padding and a run of two or more spaces is the real word gap, which is what
the `despace_line` decorator keys off to rebuild readable lines.
"""

from __future__ import annotations

import re

from job.candidate.decorators import despace_line, normalize_unicode


@normalize_unicode
@despace_line
def normalize_spaced_text(text) -> str:
    """Turn raw pypdf output into readable text, leaving normal lines untouched.

    The decorators have already folded the unicode and rebuilt the glyph-padded
    lines; what is left is the whitespace tidy-up that every line wants.
    """
    if not text:
        return ""
    lines = [re.sub(r" {2,}", " ", line).strip() for line in text.splitlines()]
    return re.sub(r"\n{3,}", "\n\n", "\n".join(lines)).strip()