增加扩胞逻辑

src/analysis/report_generator.py

@@ -97,6 +97,30 @@ class ReportGenerator:
 
         print("\n" + "=" * 70)
 
+        # 扩胞分析（新增）
+        print("\n" + "-" * 70)
+        print("【5. 扩胞需求分析】")
+        print("-" * 70)
+
+        exp = report.expansion_stats
+        total_processable = report.directly_processable + report.needs_preprocessing
+
+        if total_processable > 0:
+            print(f"  无需扩胞:             {exp['no_expansion_needed']:6d} "
+                  f"({exp['no_expansion_needed'] / total_processable:.1%})")
+            print(f"  扩胞因子=2:           {exp['expansion_factor_2']:6d}")
+            print(f"  扩胞因子=3:           {exp['expansion_factor_3']:6d}")
+            print(f"  扩胞因子=4~8:         {exp['expansion_factor_4_8']:6d}")
+            print(f"  扩胞因子>8:           {exp['expansion_factor_large']:6d}")
+            print(f"  无法扩胞(因子过大):   {exp['cannot_expand']:6d}")
+
+        # 详细分布
+        if detailed and report.expansion_factor_distribution:
+            print("\n  扩胞因子分布:")
+            for factor in sorted(report.expansion_factor_distribution.keys()):
+                count = report.expansion_factor_distribution[factor]
+                bar = "█" * min(count, 30)
+                print(f"    {factor:3d}x: {count:5d} {bar}")
     @staticmethod
     def export_to_csv(report: DatabaseReport, output_path: str):
         """导出详细结果到CSV"""

src/analysis/structure_inspector.py

@@ -1,10 +1,39 @@
 """
-结构检查器：对单个CIF文件进行深度分析
+结构检查器：对单个CIF文件进行深度分析（含扩胞需求判断）
 """
 from dataclasses import dataclass, field
 from typing import Set, Dict, List, Optional, Tuple
 from pymatgen.core import Structure
 from pymatgen.core.periodic_table import Element, Specie
+from collections import defaultdict
+from fractions import Fraction
+from functools import reduce
+import math
+import re
+import os
+
+
+@dataclass
+class OccupancyInfo:
+    """共占位信息"""
+    occupation: float  # 占据率
+    atom_serials: List[int] = field(default_factory=list)  # 原子序号
+    elements: List[str] = field(default_factory=list)  # 涉及的元素
+    numerator: int = 0  # 分子
+    denominator: int = 1  # 分母
+    involves_target_cation: bool = False  # 是否涉及目标阳离子
+    involves_anion: bool = False  # 是否涉及阴离子
+
+
+@dataclass
+class ExpansionInfo:
+    """扩胞信息"""
+    needs_expansion: bool = False  # 是否需要扩胞
+    expansion_factor: int = 1  # 扩胞因子（最小公倍数）
+    occupancy_details: List[OccupancyInfo] = field(default_factory=list)  # 共占位详情
+    problematic_sites: int = 0  # 问题位点数
+    can_expand: bool = True  # 是否可以扩胞处理
+    skip_reason: str = ""  # 无法扩胞的原因
 
 
 @dataclass
@@ -20,29 +49,34 @@ class StructureInfo:
     # 元素组成
     elements: Set[str] = field(default_factory=set)
     num_sites: int = 0
+    formula: str = ""
 
     # 阳离子/阴离子信息
     contains_target_cation: bool = False
-    anion_types: Set[str] = field(default_factory=set)  # 找到的目标阴离子
+    anion_types: Set[str] = field(default_factory=set)
     anion_mode: str = ""  # "single", "mixed", "none"
 
     # 数据质量标记
     has_oxidation_states: bool = False
     has_partial_occupancy: bool = False  # 是否有共占位
-    cation_has_partial_occupancy: bool = False  # 目标阳离子是否共占位
-    anion_has_partial_occupancy: bool = False  # 阴离子是否共占位
     has_water_molecule: bool = False
     has_radioactive_elements: bool = False
     is_binary_compound: bool = False
 
+    # 共占位详细分析（新增）
+    cation_has_partial_occupancy: bool = False  # 目标阳离子共占位
+    anion_has_partial_occupancy: bool = False  # 阴离子共占位
+    other_has_partial_occupancy: bool = False  # 其他元素共占位（需扩胞）
+    expansion_info: ExpansionInfo = field(default_factory=ExpansionInfo)
+
     # 可处理性
-    needs_expansion: bool = False  # 需要扩胞
+    needs_expansion: bool = False
-    can_process: bool = False  # 可以直接处理
+    can_process: bool = False
-    skip_reason: str = ""  # 跳过原因
+    skip_reason: str = ""
 
 
 class StructureInspector:
-    """结构检查器"""
+    """结构检查器（含扩胞分析）"""
 
     # 预定义的阴离子集合
     VALID_ANIONS = {'O', 'S', 'Cl', 'Br'}
@@ -53,16 +87,38 @@ class StructureInspector:
         'Cm', 'Bk', 'Cf', 'Es', 'Fm', 'Md', 'No', 'Lr'
     }
 
-    def __init__(self, target_cation: str = "Li", target_anions: Set[str] = None):
+    # 扩胞精度模式
+    PRECISION_LIMITS = {
+        'high': None,      # 精确分数
+        'normal': 100,     # 分母≤100
+        'low': 10,         # 分母≤10
+        'very_low': 5      # 分母≤5
+    }
+
+    def __init__(
+        self,
+        target_cation: str = "Li",
+        target_anions: Set[str] = None,
+        expansion_precision: str = "low"
+    ):
         """
         初始化检查器
 
         Args:
             target_cation: 目标阳离子 (如 "Li", "Na")
             target_anions: 目标阴离子集合 (如 {"O", "S"})
+            expansion_precision: 扩胞计算精度 ('high', 'normal', 'low', 'very_low')
         """
         self.target_cation = target_cation
         self.target_anions = target_anions or self.VALID_ANIONS
+        self.expansion_precision = expansion_precision
+
+        # 目标阳离子的各种可能表示形式
+        self.target_cation_variants = {
+            target_cation,
+            f"{target_cation}+",
+            f"{target_cation}1+",
+        }
 
     def inspect(self, file_path: str) -> StructureInfo:
         """
@@ -74,7 +130,6 @@ class StructureInspector:
         Returns:
             StructureInfo: 分析结果
         """
-        import os
         info = StructureInfo(
             file_path=file_path,
             file_name=os.path.basename(file_path)
@@ -91,9 +146,10 @@ class StructureInspector:
         # 基础信息
         info.elements = {str(el) for el in structure.composition.elements}
         info.num_sites = structure.num_sites
+        info.formula = structure.composition.reduced_formula
 
         # 检查是否为二元化合物
-        info.is_binary_compound = len(structure.types_of_specie) == 2
+        info.is_binary_compound = len(structure.composition.elements) == 2
 
         # 检查是否含有目标阳离子
         info.contains_target_cation = self.target_cation in info.elements
@@ -110,8 +166,8 @@ class StructureInspector:
         # 检查氧化态
         info.has_oxidation_states = self._check_oxidation_states(structure)
 
-        # 检查共占位
+        # 检查共占位（核心分析）
-        self._check_partial_occupancy(structure, info)
+        self._analyze_partial_occupancy(structure, info)
 
         # 检查水分子
         info.has_water_molecule = self._check_water_molecule(structure)
@@ -121,9 +177,6 @@ class StructureInspector:
             info.elements.intersection(self.RADIOACTIVE_ELEMENTS)
         )
 
-        # 判断是否需要扩胞
-        info.needs_expansion = info.has_partial_occupancy and not info.cation_has_partial_occupancy
-
         # 判断可处理性
         self._evaluate_processability(info)
 
@@ -140,48 +193,172 @@ class StructureInspector:
         except:
             return False
 
-    def _check_partial_occupancy(self, structure: Structure, info: StructureInfo):
+    def _get_element_from_species_string(self, species_str: str) -> str:
-        """检查共占位情况"""
+        """从物种字符串提取纯元素符号"""
+        match = re.match(r'([A-Z][a-z]?)', species_str)
+        return match.group(1) if match else ""
+
+    def _get_occupancy_from_species_string(self, species_str: str, exclude_elements: Set[str]) -> Optional[float]:
+        """
+        从物种字符串获取非目标元素的占据率
+        格式如: "Li+:0.689, Sc3+:0.311"
+        """
+        if ':' not in species_str:
+            return None
+
+        parts = [p.strip() for p in species_str.split(',')]
+        for part in parts:
+            if ':' in part:
+                element_part, occu_part = part.split(':')
+                element = self._get_element_from_species_string(element_part.strip())
+                if element and element not in exclude_elements:
                     try:
-            for site in structure.sites:
+                        return float(occu_part.strip())
-                if len(site.species) > 1:
+                    except ValueError:
+                        continue
+        return None
+
+    def _analyze_partial_occupancy(self, structure: Structure, info: StructureInfo):
+        """
+        分析共占位情况（核心逻辑）
+
+        关键规则：
+        - 目标阳离子(Li)的共占位 → 不可处理
+        - 阴离子的共占位 → 需要扩胞，但通常不处理
+        - 其他阳离子的共占位 → 需要扩胞处理
+        """
+        occupancy_dict = defaultdict(list)  # {occupation: [site_indices]}
+        occupancy_elements = {}  # {occupation: [elements]}
+
+        for i, site in enumerate(structure.sites):
+            site_species = site.species
+            species_string = str(site.species)
+
+            # 检查是否有多个物种占据同一位点
+            if len(site_species) > 1:
                 info.has_partial_occupancy = True
 
-                    # 检查是否涉及目标阳离子
+                # 提取各元素符号
-                    species_symbols = [str(sp.symbol) if hasattr(sp, 'symbol') else str(sp)
+                elements_at_site = []
-                                       for sp in site.species.keys()]
+                for sp in site_species.keys():
+                    elem = sp.symbol if hasattr(sp, 'symbol') else str(sp)
+                    elem = self._get_element_from_species_string(elem)
+                    if elem:
+                        elements_at_site.append(elem)
 
-                    if self.target_cation in species_symbols:
+                # 判断是否涉及目标阳离子
+                if self.target_cation in elements_at_site:
                     info.cation_has_partial_occupancy = True
 
-                    # 检查是否涉及阴离子
+                # 判断是否涉及阴离子
-                    if any(sym in self.target_anions for sym in species_symbols):
+                if any(elem in self.target_anions for elem in elements_at_site):
                     info.anion_has_partial_occupancy = True
 
+                # 判断是否涉及其他元素（需要扩胞处理的情况）
+                other_elements = [e for e in elements_at_site
+                                 if e != self.target_cation and e not in self.target_anions]
+                if other_elements:
+                    info.other_has_partial_occupancy = True
+
+                    # 获取占据率（取非目标阳离子的占据率）
+                    occu = self._get_occupancy_from_species_string(
+                        species_string,
+                        self.target_cation_variants
+                    )
+                    if occu is not None and occu != 1.0:
+                        occupancy_dict[occu].append(i)
+                        occupancy_elements[occu] = elements_at_site
+
             # 检查单一物种的部分占据
-                for specie, occupancy in site.species.items():
+            for specie, occupancy in site_species.items():
                 if occupancy < 1.0:
                     info.has_partial_occupancy = True
-                        symbol = str(specie.symbol) if hasattr(specie, 'symbol') else str(specie)
+                    elem = specie.symbol if hasattr(specie, 'symbol') else str(specie)
+                    elem = self._get_element_from_species_string(elem)
 
-                        if symbol == self.target_cation:
+                    if elem == self.target_cation:
                         info.cation_has_partial_occupancy = True
-                        if symbol in self.target_anions:
+                    elif elem in self.target_anions:
                         info.anion_has_partial_occupancy = True
-        except Exception as e:
+                    else:
-            pass
+                        info.other_has_partial_occupancy = True
+                        occupancy_dict[occupancy].append(i)
+                        occupancy_elements[occupancy] = [elem]
+
+        # 计算扩胞信息
+        self._calculate_expansion_info(info, occupancy_dict, occupancy_elements)
+
+    def _calculate_expansion_info(
+        self,
+        info: StructureInfo,
+        occupancy_dict: Dict[float, List[int]],
+        occupancy_elements: Dict[float, List[str]]
+    ):
+        """计算扩胞相关信息"""
+        expansion_info = ExpansionInfo()
+
+        if not occupancy_dict:
+            info.expansion_info = expansion_info
+            return
+
+        # 需要扩胞（有非目标阳离子的共占位）
+        expansion_info.needs_expansion = True
+        expansion_info.problematic_sites = sum(len(v) for v in occupancy_dict.values())
+
+        # 转换为OccupancyInfo列表
+        occupancy_list = []
+        for occu, serials in occupancy_dict.items():
+            elements = occupancy_elements.get(occu, [])
+
+            # 根据精度计算分数
+            limit = self.PRECISION_LIMITS.get(self.expansion_precision)
+            if limit:
+                fraction = Fraction(occu).limit_denominator(limit)
+            else:
+                fraction = Fraction(occu).limit_denominator()
+
+            occ_info = OccupancyInfo(
+                occupation=occu,
+                atom_serials=[s + 1 for s in serials],  # 转为1-based
+                elements=elements,
+                numerator=fraction.numerator,
+                denominator=fraction.denominator,
+                involves_target_cation=self.target_cation in elements,
+                involves_anion=any(e in self.target_anions for e in elements)
+            )
+            occupancy_list.append(occ_info)
+
+        expansion_info.occupancy_details = occupancy_list
+
+        # 计算最小公倍数（扩胞因子）
+        denominators = [occ.denominator for occ in occupancy_list]
+        if denominators:
+            lcm = reduce(lambda a, b: a * b // math.gcd(a, b), denominators, 1)
+            expansion_info.expansion_factor = lcm
+
+            # 判断是否可以扩胞（因子过大则不可处理）
+            if lcm > 64:  # 扩胞超过64倍通常不可行
+                expansion_info.can_expand = False
+                expansion_info.skip_reason = f"扩胞因子过大({lcm})"
+
+        info.expansion_info = expansion_info
+        info.needs_expansion = expansion_info.needs_expansion and expansion_info.can_expand
 
     def _check_water_molecule(self, structure: Structure) -> bool:
         """检查是否含有水分子"""
         try:
-            oxygen_sites = [site for site in structure.sites
+            oxygen_sites = []
-                            if 'O' in str(site.species)]
+            hydrogen_sites = []
-            hydrogen_sites = [site for site in structure.sites
+
-                              if 'H' in str(site.species)]
+            for site in structure.sites:
+                species_str = str(site.species)
+                if 'O' in species_str:
+                    oxygen_sites.append(site)
+                if 'H' in species_str:
+                    hydrogen_sites.append(site)
 
             for o_site in oxygen_sites:
-                nearby_h = [h for h in hydrogen_sites
+                nearby_h = [h for h in hydrogen_sites if o_site.distance(h) < 1.2]
-                            if o_site.distance(h) < 1.2]
                 if len(nearby_h) >= 2:
                     return True
             return False
@@ -207,15 +384,21 @@ class StructureInspector:
         if info.has_radioactive_elements:
             skip_reasons.append("含放射性元素")
 
+        # 关键：目标阳离子共占位是不可处理的
         if info.cation_has_partial_occupancy:
             skip_reasons.append(f"{self.target_cation}存在共占位")
 
+        # 阴离子共占位通常也不处理
         if info.anion_has_partial_occupancy:
             skip_reasons.append("阴离子存在共占位")
 
         if info.has_water_molecule:
             skip_reasons.append("含水分子")
 
+        # 扩胞因子过大
+        if info.expansion_info.needs_expansion and not info.expansion_info.can_expand:
+            skip_reasons.append(info.expansion_info.skip_reason)
+
         if skip_reasons:
             info.can_process = False
             info.skip_reason = "; ".join(skip_reasons)