重构3

scripts/analyze_fortran.py

@@ -25,13 +25,54 @@ def extract_commons(content):
     commons = re.findall(r'(?i)^\s*COMMON\s*/(\w+)/', content, re.MULTILINE)
     return list(set(commons))
 
-def extract_calls(content):
-    """提取 CALL 语句调用的子程序"""
-    calls = re.findall(r'(?i)CALL\s+(\w+)\s*\(', content)
-    # 也提取函数调用 ( FUNCTION 形式 )
-    funcs = re.findall(r'(?i)^\s*(?:REAL|INTEGER|DOUBLE\s*PRECISION)?\s*FUNCTION\s+(\w+)', content, re.MULTILINE)
-    # 统一转为大写
-    return list(set(c.upper() for c in calls + funcs))
+# Fortran 内置函数列表（不需要追踪）
+FORTRAN_INTRINSICS = {
+    'SIN', 'COS', 'TAN', 'ASIN', 'ACOS', 'ATAN', 'ATAN2',
+    'SINH', 'COSH', 'TANH',
+    'EXP', 'LOG', 'LOG10', 'LOG2',
+    'SQRT', 'ABS', 'MOD', 'SIGN',
+    'MAX', 'MIN', 'MAX0', 'MIN0', 'MAX1', 'MIN1', 'AMAX0', 'AMIN0',
+    'INT', 'IFIX', 'IDINT', 'FLOAT', 'SNGL', 'DBLE', 'CMPLX',
+    'REAL', 'AIMAG', 'CONJG',
+    'ICHAR', 'CHAR', 'INDEX', 'LEN', 'LGE', 'LGT', 'LLE', 'LLT',
+    'DOT_PRODUCT', 'MATMUL', 'TRANSPOSE', 'RESHAPE',
+    'SIZE', 'SHAPE', 'LBOUND', 'UBOUND',
+    'ALLOCATED', 'ALLOCATE', 'DEALLOCATE',
+    'KIND', 'SELECTED_REAL_KIND', 'SELECTED_INT_KIND',
+    'DIGITS', 'EPSILON', 'HUGE', 'TINY', 'PRECISION', 'RANGE',
+    'FLOOR', 'CEILING', 'NINT', 'ANINT',
+    'ADJUSTL', 'ADJUSTR', 'TRIM', 'REPEAT', 'SCAN', 'VERIFY',
+    'PRESENT', 'ASSOCIATED',
+    # TLUSTY 常用数学函数
+    'ERF', 'ERFC', 'GAMMA', 'LOG_GAMMA',
+}
+
+def extract_calls(content, known_functions=None):
+    """提取 CALL 语句和 FUNCTION 调用
+
+    Args:
+        content: Fortran 源码
+        known_functions: 已知的函数名集合（用于区分函数调用和数组访问）
+    """
+    calls = set()
+
+    # 1. 提取 CALL 语句（支持有括号和无括号两种形式）
+    # CALL NAME(...) 或 CALL NAME
+    call_stmts = re.findall(r'(?i)CALL\s+(\w+)(?:\s*\(|\s*$|\s*\n)', content)
+    calls.update(c.upper() for c in call_stmts)
+
+    # 2. 提取可能的 FUNCTION 调用
+    if known_functions:
+        # 只匹配已知函数名
+        func_assign = re.findall(r'(?i)=\s*([A-Z][A-Z0-9]*)\s*\(', content)
+        calls.update(f.upper() for f in func_assign
+                     if f.upper() in known_functions and f.upper() not in FORTRAN_INTRINSICS)
+
+        func_expr = re.findall(r'(?i)[=(,]\s*([A-Z][A-Z0-9]*)\s*\(', content)
+        calls.update(f.upper() for f in func_expr
+                     if f.upper() in known_functions and f.upper() not in FORTRAN_INTRINSICS)
+
+    return list(calls)
 
 def has_file_io(content):
     """检查是否有文件 I/O"""
@@ -86,6 +127,12 @@ SPECIAL_MAPPINGS = {
     'erfcx': ['erfcx', 'erfcin'],
     'lineqs': ['lineqs', 'lineqs_nr'],
     'gamsp': ['gamsp'],  # alias
+    'bhe': ['bhe', 'bhed', 'bhez'],  # 流体静力学平衡方程
+    'comset': ['comset'],  # Compton 散射参数设置
+    'ghydop': ['ghydop'],  # 氢不透明度 (Gomez 表)
+    'levgrp': ['levgrp'],  # 能级分组
+    'profil': ['profil'],  # 标准吸收轮廓
+    'linspl': ['linspl'],  # 谱线轮廓设置
 }
 
 def find_rust_module(fortran_name, rust_dir):
@@ -247,10 +294,20 @@ def main():
     extracted_dir = "/home/fmq/program/tlusty/tl208-s54/rust/tlusty/extracted"
     rust_dir = "/home/fmq/program/tlusty/tl208-s54/rust/src/math"
 
-    # 收集所有单元信息
-    units_dict = {}
+    # 第一遍：收集所有已定义的 SUBROUTINE 和 FUNCTION 名称
+    all_defined_units = set()
     fortran_files = sorted(glob.glob(os.path.join(extracted_dir, "*.f")))
 
+    for fpath in fortran_files:
+        with open(fpath, 'r', encoding='utf-8', errors='ignore') as f:
+            content = f.read()
+        units = extract_unit_info(content, os.path.basename(fpath))
+        for unit_type, unit_name in units:
+            all_defined_units.add(unit_name)
+
+    # 第二遍：收集所有单元信息（使用已知函数名来过滤调用）
+    units_dict = {}
+
     for fpath in fortran_files:
         fname = os.path.basename(fpath)
         base_name = os.path.splitext(fname)[0]
@@ -260,7 +317,7 @@ def main():
 
         includes = extract_includes(content)
         commons = extract_commons(content)
-        calls = extract_calls(content)
+        calls = extract_calls(content, known_functions=all_defined_units)
         io = has_file_io(content)
         units = extract_unit_info(content, fname)
 
@@ -315,6 +372,9 @@ def main():
         for unit_name, unit in units_dict.items():
             if unit['status'] == 'done':
                 continue
+            # 跳过无法识别程序单元的文件（如纯注释文件）
+            if unit['unit_type'] == 'UNKNOWN':
+                continue
 
             depth = calculate_depth(unit_name, units_dict, memo)
             trans_calls = len(get_transitive_deps(unit_name, units_dict))
@@ -335,10 +395,10 @@ def main():
                 'is_pure': unit['is_pure'],
             })
 
-        # 按优先级排序：未实现依赖少 > 深度低 > 无IO
-        priority_list.sort(key=lambda x: (x['trans_pending'], x['depth'], x['trans_calls'], x['has_io']))
+        # 按优先级排序：无IO > 未实现依赖少 > 深度低
+        priority_list.sort(key=lambda x: (x['has_io'], x['trans_pending'], x['depth'], x['trans_calls']))
 
-        print("重构优先级列表 (按未实现依赖排序)")
+        print("重构优先级列表 (优先无IO，按未实现依赖排序)")
         print("=" * 100)
         print(f"{'单元名':<20} {'未实现':>6} {'传递未实现':>10} {'深度':>4} {'直接调用':>8} {'传递调用':>8} {'IO':>4}")
         print("-" * 100)