Weichen Sun

"""Smali file parser — extracts individual method bodies from apktool output.

Parses .smali files produced by apktool and extracts per-method bodies,
instruction counts, and register counts.
"""

import os
import re
from dataclasses import dataclass, field
from typing import Dict, List, Optional


@dataclass
class SmaliMethod:
    """Parsed smali method data."""
    class_name: str
    method_name: str
    method_signature: str
    body: str
    instruction_count: int = 0
    register_count: int = 0
    access_flags: List[str] = field(default_factory=list)


# Directives start with '.' — these are metadata, not instructions
_DIRECTIVE_RE = re.compile(r"^\s*\.")
# Labels start with ':'
_LABEL_RE = re.compile(r"^\s*:")
# Blank or comment lines
_BLANK_OR_COMMENT_RE = re.compile(r"^\s*(#.*)?$")
# Method declaration
_METHOD_START_RE = re.compile(
    r"^\.method\s+(.*?)\s+(\S+)\(([^)]*)\)(\S+)\s*$"
)
_METHOD_START_SIMPLE_RE = re.compile(
    r"^\.method\s+(.*)"
)
# .registers or .locals directive
_REGISTERS_RE = re.compile(r"^\s*\.registers\s+(\d+)")
_LOCALS_RE = re.compile(r"^\s*\.locals\s+(\d+)")
# .line directive
_LINE_RE = re.compile(r"^\s*\.line\s+\d+")


class SmaliParser:
    """Parser for apktool smali output files."""

    @staticmethod
    def parse_smali_file(filepath: str) -> List[SmaliMethod]:
        """Parse a single .smali file and return list of methods.

        Each .smali file contains one class with all its methods.
        """
        with open(filepath, "r", encoding="utf-8", errors="replace") as f:
            content = f.read()

        return SmaliParser._parse_smali_content(content, filepath)

    @staticmethod
    def _parse_smali_content(content: str, source: str = "") -> List[SmaliMethod]:
        """Parse smali text content and extract methods."""
        lines = content.split("\n")
        methods = []

        # Extract class name from .class directive
        class_name = ""
        for line in lines:
            if line.startswith(".class "):
                parts = line.split()
                class_name = parts[-1]  # Last token is the class descriptor
                break

        in_method = False
        method_lines = []
        method_header = ""
        access_flags = []
        skip_method = False

        for line in lines:
            if line.startswith(".method "):
                in_method = True
                method_lines = []
                method_header = line
                skip_method = False

                # Parse access flags and method signature
                remainder = line[len(".method "):].strip()
                tokens = remainder.split()
                access_flags = []
                method_sig_token = tokens[-1] if tokens else ""

                for t in tokens[:-1]:
                    access_flags.append(t)

                # Skip abstract and native methods (no body)
                if "abstract" in access_flags or "native" in access_flags:
                    skip_method = True

            elif line.startswith(".end method"):
                if in_method and not skip_method:
                    body = "\n".join(method_lines)
                    method_name, signature = SmaliParser._parse_method_sig(
                        method_header
                    )
                    instruction_count = SmaliParser.count_instructions(body)
                    register_count = SmaliParser._extract_register_count(body)

                    methods.append(
                        SmaliMethod(
                            class_name=class_name,
                            method_name=method_name,
                            method_signature=signature,
                            body=body,
                            instruction_count=instruction_count,
                            register_count=register_count,
                            access_flags=access_flags,
                        )
                    )
                in_method = False
                method_lines = []
                access_flags = []

            elif in_method and not skip_method:
                method_lines.append(line)

        return methods

    @staticmethod
    def parse_smali_directory(dirpath: str) -> Dict[str, SmaliMethod]:
        """Parse all .smali files in a directory tree.

        Returns dict keyed by 'ClassName->methodName(signature)ReturnType'.
        """
        result = {}
        for root, _dirs, files in os.walk(dirpath):
            for fname in files:
                if fname.endswith(".smali"):
                    fpath = os.path.join(root, fname)
                    try:
                        methods = SmaliParser.parse_smali_file(fpath)
                        for m in methods:
                            key = SmaliParser.make_method_key(
                                m.class_name, m.method_name, m.method_signature
                            )
                            result[key] = m
                    except Exception:
                        continue
        return result

    @staticmethod
    def normalize_smali_body(body: str) -> str:
        """Normalize smali body for consistent hashing.

        Strips comments, .line directives, normalizes whitespace.
        """
        lines = []
        for line in body.split("\n"):
            stripped = line.strip()
            # Skip empty lines, comments, and .line directives
            if not stripped or stripped.startswith("#"):
                continue
            if _LINE_RE.match(stripped):
                continue
            lines.append(stripped)
        return "\n".join(lines)

    @staticmethod
    def count_instructions(body: str) -> int:
        """Count actual Dalvik instructions (skip directives, labels, blanks)."""
        count = 0
        for line in body.split("\n"):
            stripped = line.strip()
            if not stripped:
                continue
            if _DIRECTIVE_RE.match(stripped):
                continue
            if _LABEL_RE.match(stripped):
                continue
            if _BLANK_OR_COMMENT_RE.match(stripped):
                continue
            count += 1
        return count

    @staticmethod
    def _extract_register_count(body: str) -> int:
        """Extract register count from .registers or .locals directive.

        apktool outputs .locals (local registers only) by default.
        .registers (total = locals + params) is used with --use-registers.
        We return whichever is present.
        """
        for line in body.split("\n"):
            stripped = line.strip()
            m = _REGISTERS_RE.match(stripped)
            if m:
                return int(m.group(1))
            m = _LOCALS_RE.match(stripped)
            if m:
                return int(m.group(1))
        return 0

    @staticmethod
    def _parse_method_sig(header_line: str) -> tuple:
        """Parse method name and signature from .method header line.

        Input: '.method public onCreate(Landroid/os/Bundle;)V'
        Returns: ('onCreate', '(Landroid/os/Bundle;)V')
        """
        remainder = header_line[len(".method "):].strip()
        tokens = remainder.split()
        if not tokens:
            return ("unknown", "()")

        # Last token contains methodName(params)returnType
        method_part = tokens[-1]

        paren_idx = method_part.find("(")
        if paren_idx == -1:
            return (method_part, "()")

        method_name = method_part[:paren_idx]
        signature = method_part[paren_idx:]

        return (method_name, signature)

    @staticmethod
    def make_method_key(class_name: str, method_name: str, signature: str) -> str:
        """Build a canonical method key for cross-tool matching.

        Format: 'Lcom/example/Foo;->methodName(params)ReturnType'
        """
        return f"{class_name}->{method_name}{signature}"