构建mars_toolkit,删除tools_for_ms

mars_toolkit/core/cif_utils.py

@@ -0,0 +1,121 @@
+"""
+CIF Utilities Module
+
+This module provides basic functions for handling CIF (Crystallographic Information File) files,
+which are commonly used in materials science for representing crystal structures.
+
+Author: Yutang LI
+Institution: SIAT-MIC
+Contact: yt.li2@siat.ac.cn
+"""
+
+import json
+import logging
+
+logger = logging.getLogger(__name__)
+
+def read_cif_txt_file(file_path):
+    """
+    Read the CIF file and return its content.
+
+    Args:
+        file_path: Path to the CIF file
+
+    Returns:
+        String content of the CIF file or None if an error occurs
+    """
+    try:
+        with open(file_path, 'r', encoding='utf-8') as f:
+            return f.read()
+    except Exception as e:
+        logger.error(f"Error reading file {file_path}: {e}")
+        return None
+
+def extract_cif_info(path: str, fields_name: list):
+    """
+    Extract specific fields from the CIF description JSON file.
+
+    Args:
+        path: Path to the JSON file containing CIF information
+        fields_name: List of field categories to extract. Use 'all_fields' to extract all fields.
+                    Other options include 'basic_fields', 'energy_electronic_fields', 'metal_magentic_fields'
+
+    Returns:
+        Dictionary containing the extracted fields
+    """
+    basic_fields = ['formula_pretty', 'chemsys', 'composition', 'elements', 'symmetry', 'nsites', 'volume', 'density']
+    energy_electronic_fields = ['formation_energy_per_atom', 'energy_above_hull', 'is_stable', 'efermi', 'cbm', 'vbm', 'band_gap', 'is_gap_direct']
+    metal_magentic_fields = ['is_metal', 'is_magnetic', "ordering", 'total_magnetization', 'num_magnetic_sites']
+
+    selected_fields = []
+    if fields_name[0] == 'all_fields':
+        selected_fields = basic_fields + energy_electronic_fields + metal_magentic_fields
+    else:
+        for field in fields_name:
+            selected_fields.extend(locals().get(field, []))
+
+    with open(path, 'r') as f:
+        docs = json.load(f)
+
+    new_docs = {}
+    for field_name in selected_fields:
+        new_docs[field_name] = docs.get(field_name, '')
+
+    return new_docs
+
+def remove_symmetry_equiv_xyz(cif_content):
+    """
+    Remove symmetry operations section from CIF file content.
+
+    This is often useful when working with CIF files in certain visualization tools
+    or when focusing on the basic structure without symmetry operations.
+
+    Args:
+        cif_content: CIF file content string
+
+    Returns:
+        Cleaned CIF content string with symmetry operations removed
+    """
+    lines = cif_content.split('\n')
+    output_lines = []
+
+    i = 0
+    while i < len(lines):
+        line = lines[i].strip()
+
+        # 检测循环开始
+        if line == 'loop_':
+            # 查看下一行，检查是否是对称性循环
+            next_lines = []
+            j = i + 1
+            while j < len(lines) and lines[j].strip().startswith('_'):
+                next_lines.append(lines[j].strip())
+                j += 1
+
+            # 检查是否包含对称性操作标签
+            if any('_symmetry_equiv_pos_as_xyz' in tag for tag in next_lines):
+                # 跳过整个循环块
+                while i < len(lines):
+                    if i + 1 >= len(lines):
+                        break
+
+                    next_line = lines[i + 1].strip()
+                    # 检查是否到达下一个循环或数据块
+                    if next_line == 'loop_' or next_line.startswith('data_'):
+                        break
+
+                    # 检查是否到达原子位置部分
+                    if next_line.startswith('_atom_site_'):
+                        break
+
+                    i += 1
+            else:
+                # 不是对称性循环，保留loop_行
+                output_lines.append(lines[i])
+        else:
+            # 非循环开始行，直接保留
+            output_lines.append(lines[i])
+
+        i += 1
+
+    return '\n'.join(output_lines)