rag-from-scratch/conversione/_pipeline/_constants.py

"""
Costanti di modulo condivise tra i moduli di trasformazione.
Tutte le regex compilate e le mappe statiche vivono qui.
"""
import re

# ─── Keyword sets ─────────────────────────────────────────────────────────────

_TOC_KEYWORDS = frozenset([
    "indice", "index", "contents", "table of contents",
    "sommario", "inhaltsverzeichnis", "inhalt",
    "indice generale", "indice analitico", "indice dei contenuti",
    "elenco dei capitoli", "argomenti", "table des matières",
    "tabla de contenidos", "содержание",
])

_ORDINALS_IT = {
    "PRIMO": "I", "SECONDO": "II", "TERZO": "III", "QUARTO": "IV",
    "QUINTO": "V", "SESTO": "VI", "SETTIMO": "VII", "OTTAVO": "VIII",
    "NONO": "IX", "DECIMO": "X",
}
_ORDINALS_EN = {
    "ONE": "1", "TWO": "2", "THREE": "3", "FOUR": "4", "FIVE": "5",
    "SIX": "6", "SEVEN": "7", "EIGHT": "8", "NINE": "9", "TEN": "10",
}

# ─── PUA Symbol font map ──────────────────────────────────────────────────────

_SYMBOL_PUA_MAP: dict[str, str] = {
    "": " ",
    "": "(",
    "": ")",
    "": "+",
    "": "−",
    "": ".",
    "": "/",
    "": "0", "": "1", "": "2", "": "3", "": "4",
    "": "5", "": "6", "": "7", "": "8", "": "9",
    "": ":", "": ";", "": "<", "": "=", "": ">",
    "": "≅",
    "": "Α", "": "Β", "": "Χ", "": "Δ", "": "Ε",
    "": "Φ", "": "Γ", "": "Η", "": "Ι", "": "ϑ",
    "": "Κ", "": "Λ", "": "Μ", "": "Ν", "": "Ο",
    "": "Π", "": "Θ", "": "Ρ", "": "Σ", "": "Τ",
    "": "Υ", "": "ς", "": "Ω", "": "Ξ", "": "Ψ",
    "": "Ζ",
    "": "[",
    "": "∴",
    "": "]",
    "": "⊥",
    "": "α", "": "β", "": "χ", "": "δ", "": "ε",
    "": "φ", "": "γ", "": "η", "": "ι", "": "ϕ",
    "": "κ", "": "λ", "": "μ", "": "ν", "": "ο",
    "": "π", "": "θ", "": "ρ", "": "σ", "": "τ",
    "": "υ", "": "ϖ", "": "ω", "": "ξ", "": "ψ",
    "": "ζ",
    "": "{",
    "": "|",
    "": "}",
    "": "~",
    "": "±",
    "": "•",
    "": "√",
    "": "≤",
    "": "≥",
    "": "∝",
    "": "×",
    "": "÷",
    "": "×",
    "": "≠",
    "": "≠",
    "": "≥",
    "": "′",
    "": "*",
    "": ",",
    "": "≤",
    "": "•",
    "": "•",
    "": "→",
    "": "÷",
    "": "",
    "": "→",
    "": "",
    "": "",
    "": "",
    "": "",
    # TeX Computer Modern bracket/delimiter pieces (U+F8EB–F8FE) → stringa vuota
    "": "",  # TeX large paren left
    "": "",  # TeX large paren extension
    "": "",  # TeX large paren right
    "": "",  # TeX large paren right ext
    "": "",  # TeX large bracket left
    "": "",  # TeX large bracket ext
    "": "",  # TeX brace top-left
    "": "",  # TeX brace mid
    "": "",  # TeX brace mid-right
    "": "",  # TeX brace extension
    "": "",  # TeX brace right
    "": "",  # TeX bracket right large
    "": "",  # TeX bracket right ext
    "": "",  # TeX bracket right close
    "": "",  # TeX integral large
    "": "",  # TeX integral extension
    "": "",  # TeX integral top
    "": "",  # TeX radical top
    "": "",  # TeX radical extension
    "": "",  # TeX arrowhead
}

_SYMBOL_PUA_RE = re.compile(
    "[" + "".join(re.escape(k) for k in _SYMBOL_PUA_MAP) + "]"
)

# ─── Regex compilate condivise ────────────────────────────────────────────────

_SUPERSCRIPT_RE = re.compile(r'[¹²³⁰⁴-⁹]+')
_FOOTNOTE_BODY_RE = re.compile(
    r'^([¹²³⁰⁴-⁹]+\s+|\[\d{1,3}\]\s+)'
)
_NUMBERED_HDR_RE = re.compile(
    r"^(#{1,6})\s+(\d+(?:\.\d+)*)\.\s+(.+)$",
    re.MULTILINE,
)
_BIB_MARKERS_RE = re.compile(
    r'\b(pp?\.|vol\.|n\.\s*\d|ed\.|edn\.|ISBN|DOI|arXiv)\b'
    r'|\b(19|20)\d{2}\b'
    r'|\b(ibid\.?|ibidem|op\.\s*cit\.?|cit\.|cfr\.|ivi[,;\s])\b',
    re.IGNORECASE,
)
# Pattern autore accademico: iniziale maiuscola + cognome TUTTO-MAIUSCOLO (es. A. PAJNO, G. GUZZETTA)
_FOOTNOTE_AUTHOR_RE = re.compile(r'(?<![A-Z])[A-Z]\.\s+[A-Z]{3,}')
_WATERMARK_RE = re.compile(
    r"^(BOZZA|DRAFT|CONFIDENTIAL|RISERVATO|PROVVISORIO|SAMPLE|SPECIMEN"
    r"|DO NOT DISTRIBUTE|NON DISTRIBUIRE|COPY|COPIA)\s*$",
    re.IGNORECASE | re.MULTILINE,
)
_TABSEP_RE = re.compile(r"(?m)^\|\s*\|\s*$|^\|---\|?\s*$")
_DOTLEADER_RE = re.compile(r"^[^\n]*(?:(?:\. ){3,}|\.{4,})[^\n]*$", re.MULTILINE)
_FM_RE = re.compile(
    r"https?://|www\.|@[A-Za-z]|\bUniversit[àa]\b|\bDipartimento\b|"
    r"\bCopyright\b|\bLicenza\b|\bEdizione\b|"
    r"protetto da|tutti i diritti",
    re.IGNORECASE,
)
_VERSE_NUM_RE = re.compile(
    r"([.!?\xbb'\"" + "’" + r"]\s+)(\d+)(\s+)(?=[A-Z\xc0-\xd9a-z\xe0-\xf9\xab“”‟])"
)
# Math header demotion
_MATH_SYMBOLS_RE = re.compile(
    r"[=+∈∀∃≤≥∞∑∫∂→↔⊂⊃∩∪αβγδεζηθικλμνξοπρστυφχψωΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩ]"
)
_EXERCISE_TRIGGER_RE = re.compile(
    r"\b(Si dimostri|Si calcoli|Si provi|Si trovi|Trovare|Find|Prove|Show that"
    r"|Compute|Calculate|Dimostrare|Verificare)\b",
    re.IGNORECASE,
)
_MATH_HDR_RE = re.compile(r"^(#{2,3})\s+(.+)$")
_NUMBERED_PREFIX_RE = re.compile(r"^(\d+(?:\.\d+)*[.)])\s+(.+)$", re.DOTALL)
# Orphan TOC: voce di indice senza dot-leader (es. "3. Funzioni 174")
_TOC_ITEM_RE = re.compile(
    r"^\d+(\.\d+)*\.?\s+[A-Za-zÀ-ú\'\(][^\n]{2,70}$"
)
_TOC_HDR_WITH_PAGE_RE = re.compile(
    r"^#{1,3}\s+\d+\.?\s+.{3,60}\s+\d{1,4}$"
)
# Artefatti PDF: page markers e separatori
_PAGE_MARKER_RE = re.compile(r"(?m)^<!-- page: \d+ -->\s*$")
_STANDALONE_NUM_RE = re.compile(r"(?m)^(?:- )?\d{1,3}$")
_UNDERSCORE_SEP_RE = re.compile(r"(?m)^_{4,}\s*$")