From 2e8b78ab0ef01eaacd8094ff839ac93b4451e9c3 Mon Sep 17 00:00:00 2001
From: Aargh Rai <aargh.rai+git@gmail.com>
Date: Fri, 10 Jul 2026 23:12:04 +0530
Subject: symbol analyzer init

---
 symbol_analyzer/extractor.py | 56 ++++++++++++++++++++++++++++++++++++++
 symbol_analyzer/main.py      | 26 ++++++++++++++++++
 symbol_analyzer/parser.py    | 65 ++++++++++++++++++++++++++++++++++++++++++++
 symbol_analyzer/symbols.py   | 17 ++++++++++++
 4 files changed, 164 insertions(+)
 create mode 100644 symbol_analyzer/extractor.py
 create mode 100644 symbol_analyzer/main.py
 create mode 100644 symbol_analyzer/parser.py
 create mode 100644 symbol_analyzer/symbols.py

(limited to 'symbol_analyzer')

diff --git a/symbol_analyzer/extractor.py b/symbol_analyzer/extractor.py
new file mode 100644
index 0000000..0e8694c
--- /dev/null
+++ b/symbol_analyzer/extractor.py
@@ -0,0 +1,56 @@
+def parse_file(file):
+    f = open(file)
+    contents = f.read()
+    f.close()
+
+    significant_token = ""
+    depth = 0
+    tokens = []
+    swallen_tokens = [0, 0]
+    token_buffer = ""
+    define_striping = False
+    for c in contents:
+        if c == " " or c == "{" or c == "}" or \
+            c == ";" or c == ":" or c == "[" or c == "]" or \
+            c == "(" or c == ")" or c == "," or c == "\n" or c == "*":
+
+            if significant_token == "":
+                if c == "{" or c == "}":
+                    depth += 1 if c == "{" else -1
+            elif significant_token == "#define":
+                if tokens[-1] == ")":
+                    define_striping = True
+                    depth = 1
+                if swallen_tokens[-2] != "\\" and swallen_tokens[-1] == "\n":
+                    significant_token = ""
+                    define_striping = False
+                    depth = 0
+            else:
+                depth = 0
+                if swallen_tokens[-1] == ";":
+                    significant_token = ""
+
+            if depth == 0:
+                if len(token_buffer) > 0:
+                    if token_buffer in ["#define", "enum", "struct"]:
+                        significant_token = token_buffer
+                    tokens.append(token_buffer)
+                if c != ' ' and len(c) > 0:
+                    tokens.append(c)
+            else:
+                if len(token_buffer) > 0:
+                    if token_buffer in ["#define", "enum", "struct"]:
+                        significant_token = token_buffer
+                    swallen_tokens.append(token_buffer)
+                if c != ' ' and len(c) > 0:
+                    swallen_tokens.append(c)
+
+            token_buffer = ""
+            continue
+
+        token_buffer += c
+
+    if depth == 0 and len(token_buffer) > 0:
+        tokens.append(token_buffer)
+
+    return tokens, swallen_tokens
diff --git a/symbol_analyzer/main.py b/symbol_analyzer/main.py
new file mode 100644
index 0000000..1fa5457
--- /dev/null
+++ b/symbol_analyzer/main.py
@@ -0,0 +1,26 @@
+import os
+
+from extractor import parse_file
+from parser import parse_definition_tokens
+from symbols import symbols_from_struct_tokens, symbols_from_enum_tokens
+
+symbols = set()
+
+for root, subdirs, files in os.walk("include"):
+    for file in files:
+        file_symbols = ["int", "bool", "char"]
+        definitions, usage = parse_file(root + "/" + file)
+        structs, enums, functions, typedefs = parse_definition_tokens(
+            definitions,
+            file_symbols
+        )
+        file_symbols.extend(symbols_from_struct_tokens(structs))
+        file_symbols.extend(symbols_from_enum_tokens(enums))
+        file_symbols.extend(functions)
+        file_symbols.extend(typedefs)
+        for item in file_symbols:
+            if item.isnumeric():
+                continue
+            symbols.add(item)
+
+print(symbols)
diff --git a/symbol_analyzer/parser.py b/symbol_analyzer/parser.py
new file mode 100644
index 0000000..551857e
--- /dev/null
+++ b/symbol_analyzer/parser.py
@@ -0,0 +1,65 @@
+def parse_definition_tokens(tokens, symbols):
+    typedeffed = False
+    simple_typedefs = []
+    structs = []
+    enums = []
+    functions = []
+
+    i = 0
+    while i < len(tokens):
+        # skip comments
+        if tokens[i] == "//":
+            while tokens[i] != "\n":
+                i += 1
+            i += 1
+            continue
+        if tokens[i] == "typedef":
+            if tokens[i + 1] in symbols:
+                simple_typedefs.append(tokens[i + 2])
+                i += 2
+        if tokens[i] == "struct":
+            i += 1
+            defs = []
+            depth = 0
+            while True:
+                if tokens[i] == "//":
+                    while tokens[i] != "\n":
+                        i += 1
+                    i += 1
+                    continue
+                if tokens[i] == ";":
+                    if depth == 0:
+                        break
+                if tokens[i] == "{":
+                    depth += 1
+                if tokens[i] == "}":
+                    depth -= 1
+                defs.append(tokens[i])
+                i += 1
+            structs.append(defs)
+        if tokens[i] == "enum":
+            i += 1
+            defs = []
+            depth = 0
+            while True:
+                if tokens[i] == "//":
+                    while tokens[i] != "\n":
+                        i += 1
+                    i += 1
+                    continue
+                if tokens[i] == ";":
+                    if depth == 0:
+                        break
+                if tokens[i] == "{":
+                    depth += 1
+                if tokens[i] == "}":
+                    depth -= 1
+                defs.append(tokens[i])
+                i += 1
+            enums.append(defs)
+        i += 1
+
+        if tokens[i] == "(":
+            functions.append(tokens[i - 1])
+
+    return structs, enums, functions, simple_typedefs
diff --git a/symbol_analyzer/symbols.py b/symbol_analyzer/symbols.py
new file mode 100644
index 0000000..7384d33
--- /dev/null
+++ b/symbol_analyzer/symbols.py
@@ -0,0 +1,17 @@
+def symbols_from_struct_tokens(tokens):
+    symbols = []
+    for struct in tokens:
+        if struct[0] == "{":
+            symbols.append(struct[-1])
+        else:
+            symbols.append(struct[0])
+    return symbols
+
+def symbols_from_enum_tokens(tokens):
+    symbols = []
+    for enum in tokens:
+        for token in enum:
+            if token == "{" or token == "}" or token == ",":
+                continue
+            symbols.append(token)
+    return symbols
-- 
cgit v1.2.3