DoLuEdu-WordFileParse/scripts/omml_mathml2latex/utils/chemistry_detection.py

"""
Chemistry equation detection utilities.

This module provides functions to detect whether an equation is chemistry-related
based on strong indicators like multi-char elements, charges, and reaction arrows.
"""

from lxml import etree as ET
from typing import Optional, Tuple
from ..data.chemistry_data import (
    MULTI_CHAR_ELEMENTS,
    ALL_CHEMICAL_ELEMENTS,
    CHEMICAL_GROUPS,
    CHINESE_CHEMICAL_TERMS,
)


def detect_chemistry_equation(root: ET.Element) -> bool:
    """
    Detect if equation is chemistry-related using STRONG indicators only.

    DISABLED: Subject detection is obsolete. We rely on mathvariant="normal" only.
    Chemistry formulas are properly formatted when MathML includes mathvariant="normal".

    Args:
        root: The root MathML element (<math>)

    Returns:
        False - always (chemistry detection disabled)
    """
    # DISABLED: Always return False - no heuristic chemistry detection
    return False

    # OLD CODE (kept for reference):
    # Strong indicators:
    # 1. Multi-char chemical elements in single <mi> tag (Cu, Al, Fe, Mn, etc.)
    # 2. Chemical groups (OH, SO, NO, CO, NH)
    # 3. Element + numeric subscript (H₂O pattern)
    # 4. Electric charges in superscript (^{2+}, ^{2-})
    # 5. Chemical arrows (↑, ↓)
    # 6. Chinese chemical terms (高温, 电解, etc.)
    #
    # for node in root.iter():
    #     # Remove namespace if present
    #     tag = node.tag.split('}')[-1] if '}' in node.tag else node.tag
    #     text = (node.text or '').strip()
    #
    #     # Strong indicator 1: Multi-char element in single <mi>
    #     if tag == 'mi' and text in MULTI_CHAR_ELEMENTS:
    #         return True
    #
    #     # Strong indicator 2: Chemical group
    #     if tag == 'mtext' and text in CHEMICAL_GROUPS:
    #         return True
    #
    #     # Strong indicator 3: Element + numeric subscript (H₂O, SO₄ pattern)
    #     if tag == 'msub' and len(node) >= 2:
    #         base_node = node[0]
    #         sub_node = node[1]
    #         base_text = (base_node.text or '').strip()
    #         sub_text = (sub_node.text or '').strip()
    #
    #         # Element with numeric subscript
    #         if base_text in ALL_CHEMICAL_ELEMENTS and sub_text.isdigit():
    #             return True
    #
    #     # Strong indicator 4: Electric charge superscript (Cu^{2+}, Mn^{2-})
    #     if tag == 'msup' and len(node) >= 2:
    #         sup_node = node[1]
    #         sup_text = (sup_node.text or '').strip()
    #
    #         # Check for charge notation (contains + or -)
    #         # Pattern: "2+", "+", "2-", "-", "3+", etc.
    #         if sup_text and ('+' in sup_text or '-' in sup_text):
    #             # Additional check: ensure it's likely a charge, not math
    #             # Charges are typically: digit* followed by +/-
    #             # Math would be expressions like "x+1", "y-2"
    #             # Simple heuristic: if it's short and has +/- at end, it's likely a charge
    #             if len(sup_text) <= 3 and (sup_text.endswith('+') or sup_text.endswith('-')):
    #                 return True
    #             # Also check for format: "2 +" or "2 -" (with space)
    #             parts = sup_text.split()
    #             if len(parts) == 2 and parts[0].isdigit() and parts[1] in ('+', '-'):
    #                 return True
    #
    #     # Strong indicator 5: Chemical arrows (precipitate, gas)
    #     if tag == 'mo' and text in ('↑', '↓'):
    #         return True
    #
    #     # Strong indicator 6: Chinese chemical terms
    #     if tag in ('mtext', 'mi') and text in CHINESE_CHEMICAL_TERMS:
    #         return True
    #
    # return False


def calculate_chemistry_probability(root: ET.Element, subject_mode: Optional[str] = None) -> float:
    """
    Calculate chemistry probability score based on multiple indicators.

    Scoring weights:
    - Ion charge present (^{2+}, ^{3-}): +1.0
    - Multi-char element in single <mi>: +0.8
    - Nearby multi-char element: +0.8
    - Reaction arrow (→, ⇌, ⇄): +0.6
    - Chemical subscripts (H_2, O_2): +0.4
    - Chinese chemical term: +0.3
    - User set --subject chemistry: +0.5

    Thresholds:
    - Chemistry mode: ≥0.8 (merge fragmented elements)
    - Auto-mode: ≥1.5 (only VERY strong indicators)

    Args:
        root: The root MathML element (<math>)
        subject_mode: Optional subject mode ('chemistry', 'physics', etc.)

    Returns:
        Probability score (0.0-3.0+)

    Examples:
        >>> # M n^{2+} with MnO nearby: 1.0 + 0.8 + 0.8 = 2.6 (strong)
        >>> calculate_chemistry_probability(math_root)  # 2.6

        >>> # Just "M n" with no context: 0.0 (weak)
        >>> calculate_chemistry_probability(math_root)  # 0.0

        >>> # Chemistry mode boost: M n → 0.5 (mode) + context
        >>> calculate_chemistry_probability(math_root, 'chemistry')  # 0.5+
    """
    # DISABLED: Always return 0.0 - no chemistry detection
    return 0.0

    # OLD CODE (kept for reference):
    # score = 0.0
    # # Mode boost: user explicitly set --subject chemistry
    # if subject_mode == 'chemistry':
    #     score += 0.5
    #
    # # Counters for various indicators
    # has_ion_charge = False
    # multi_char_element_count = 0
    # has_reaction_arrow = False
    # chemical_subscript_count = 0
    # has_chinese_term = False
    #
    # for node in root.iter():
    #     # Remove namespace if present
    #     tag = node.tag.split('}')[-1] if '}' in node.tag else node.tag
    #     text = (node.text or '').strip()
    #
    #     # Indicator 1: Multi-char element in single <mi> (+0.8 each, max 2)
    #     if tag == 'mi' and text in MULTI_CHAR_ELEMENTS:
    #         multi_char_element_count += 1
    #
    #     # Indicator 2: Chemical group (+0.8)
    #     if tag == 'mtext' and text in CHEMICAL_GROUPS:
    #         multi_char_element_count += 1
    #
    #     # Indicator 3: Element + numeric subscript (H₂O pattern) (+0.4 each, max 3)
    #     if tag == 'msub' and len(node) >= 2:
    #         base_node = node[0]
    #         sub_node = node[1]
    #         base_text = (base_node.text or '').strip()
    #         sub_text = (sub_node.text or '').strip()
    #
    #         if base_text in ALL_CHEMICAL_ELEMENTS and sub_text.isdigit():
    #             chemical_subscript_count += 1
    #
    #     # Indicator 4: Ion charge superscript (+1.0, strongest indicator)
    #     if tag == 'msup' and len(node) >= 2:
    #         sup_node = node[1]
    #         sup_text = (sup_node.text or '').strip()
    #
    #         # Check for charge notation
    #         if sup_text and ('+' in sup_text or '-' in sup_text):
    #             if len(sup_text) <= 3 and (sup_text.endswith('+') or sup_text.endswith('-')):
    #                 has_ion_charge = True
    #             # Also check for format: "2 +" or "2 -"
    #             parts = sup_text.split()
    #             if len(parts) == 2 and parts[0].isdigit() and parts[1] in ('+', '-'):
    #                 has_ion_charge = True
    #
    #     # Indicator 5: Reaction arrows (+0.6)
    #     if tag == 'mo':
    #         # Chemical arrows (precipitate, gas)
    #         if text in ('↑', '↓'):
    #             has_reaction_arrow = True
    #         # Reaction arrows (→, ⇌, ⇄, etc.)
    #         if text in ('→', '←', '⇌', '⇄', '⟶', '⟵', '⇀', '↽'):
    #             has_reaction_arrow = True
    #
    #     # Indicator 6: Chinese chemical terms (+0.3)
    #     if tag in ('mtext', 'mi') and text in CHINESE_CHEMICAL_TERMS:
    #         has_chinese_term = True
    #
    # # Calculate total score
    # if has_ion_charge:
    #     score += 1.0
    #
    # # Cap multi-char elements at 2 (prevent over-scoring)
    # score += min(multi_char_element_count, 2) * 0.8
    #
    # if has_reaction_arrow:
    #     score += 0.6
    #
    # # Cap chemical subscripts at 3
    # score += min(chemical_subscript_count, 3) * 0.4
    #
    # if has_chinese_term:
    #     score += 0.3
    #
    # return score


def detect_chemistry_equation_with_probability(root: ET.Element) -> Tuple[bool, float]:
    """
    Detect chemistry equation and return both boolean and probability score.

    DISABLED: Subject detection is obsolete.

    Args:
        root: The root MathML element (<math>)

    Returns:
        Tuple of (False, 0.0) - always (chemistry detection disabled)
    """
    # DISABLED: Always return (False, 0.0)
    return False, 0.0

    # OLD CODE (kept for reference):
    # probability = calculate_chemistry_probability(root)
    # is_chemistry = probability >= 1.0  # Strong indicator threshold
    # return is_chemistry, probability


def is_chemistry_variable(text: str, in_chemistry_context: bool) -> bool:
    """
    Determine if text is a chemistry variable (should stay italic).

    DISABLED: Chemistry detection is obsolete.

    Args:
        text: The identifier text
        in_chemistry_context: Whether we're in a chemistry equation (ignored)

    Returns:
        False - always (not used anymore)
    """
    # DISABLED: Always return False - chemistry detection disabled
    return False

    # OLD CODE (kept for reference):
    # from ..data.chemistry_data import CHEMISTRY_VARIABLES
    # # In chemistry context, check if it's a known variable
    # if in_chemistry_context:
    #     return text in CHEMISTRY_VARIABLES
    # # Not in chemistry context, not a chemistry variable
    # return False