chore(flutter): analyzer cleanup phase 1.2 (tools)

[zensgit]

Add robust unused-imports fixer and material import adder to support mechanical cleanup runs. No behavior changes.

[gemini-code-assist]

Summary of Changes

Hello @zensgit, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces new tooling and enhances existing scripts to automate code cleanup in Flutter projects. It adds a new utility to ensure proper material.dart imports are present when Material Design components are used, and it substantially upgrades the existing unused import fixer for greater robustness and flexibility. These changes aim to streamline mechanical code hygiene runs, making the codebase cleaner and more consistent without altering application behavior.

Highlights

• New Material Import Fixer: A new Python script, fix_missing_material_imports.py, has been added. This script automatically detects and inserts package:flutter/material.dart imports into Dart files when Material Design components (like Icons, Colors, or ElevatedButton) are used without the necessary import, acting conservatively to avoid redundant additions.
• Enhanced Unused Imports Fixer: The existing fix_unused_imports.py script has been significantly refactored and improved. It now supports command-line arguments via argparse (including --from-file to parse pre-saved analyzer output and --dry-run), features more robust parsing of flutter analyze output with multiple regex patterns, and includes refined logic for removing unused imports while handling various quote styles and de-duplicating findings.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[Copilot]

Pull Request Overview

Adds two robust utility tools for automated Flutter codebase cleanup: an unused imports fixer and a material import adder. These tools support mechanical cleanup runs with improved parsing, error handling, and command-line options including dry-run mode.

• Enhanced unused imports fixer with regex-based parsing, deduplication, and flexible input options
• New material import adder for automatically detecting and adding missing material.dart imports
• Improved error handling and command-line argument support for both tools

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

File	Description
jive-flutter/fix_unused_imports.py	Complete rewrite with robust regex parsing, deduplication logic, and CLI arguments
jive-flutter/fix_missing_material_imports.py	New utility to automatically add material.dart imports when Flutter UI components are detected

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

The import insertion logic will place the material import after all existing imports, but it should be inserted in the correct alphabetical order among other package imports to follow Dart conventions. Consider sorting imports or finding the appropriate position among package imports.

Suggested change

	# Insert after first import line block, or at top if none
	insert_idx = 0
	while insert_idx < len(lines) and lines[insert_idx].strip().startswith('import '):
	insert_idx += 1
	lines.insert(insert_idx, "import 'package:flutter/material.dart';\n")
	# Find all import lines and their indices
	import_lines = []
	for idx, line in enumerate(lines):
	if line.strip().startswith('import '):
	import_lines.append((idx, line.strip()))
	# Find the range of package: imports
	package_imports = [(idx, l) for idx, l in import_lines if l.startswith("import 'package:")]
	material_import = "import 'package:flutter/material.dart';\n"
	if package_imports:
	# Find the correct alphabetical position among package imports
	insert_idx = package_imports[0][0]
	inserted = False
	for i, (idx, l) in enumerate(package_imports):
	import_path = l.split('import ')[1].strip(';').strip("'").strip('"')
	if material_import.strip() < l:
	insert_idx = idx
	lines.insert(insert_idx, material_import)
	inserted = True
	break
	if not inserted:
	# Insert after the last package import
	insert_idx = package_imports[-1][0] + 1
	lines.insert(insert_idx, material_import)
	else:
	# Insert after all imports, or at the top if none
	insert_idx = 0
	for idx, line in enumerate(lines):
	if line.strip().startswith('import '):
	insert_idx = idx + 1
	lines.insert(insert_idx, material_import)

[Copilot]

The file is read twice - once in the main loop and again in add_material_import(). This is inefficient and could be optimized by passing the already-read text to the add_material_import() function.

[Copilot]

The simple string search for 'package:flutter/material.dart' could match commented-out imports or imports within string literals. Consider using a more precise regex pattern to match actual import statements.

Suggested change

	def file_needs_material(text: str) -> bool:
	if 'package:flutter/material.dart' in text:
	MATERIAL_IMPORT_RE = re.compile(
	r"^\s*import\s+['\"]package:flutter/material\.dart['\"]", re.MULTILINE
	)
	def file_needs_material(text: str) -> bool:
	if MATERIAL_IMPORT_RE.search(text):

[gemini-code-assist]

Code Review

This pull request introduces two helpful Python scripts for maintaining the Flutter codebase: one to add missing material imports and another to remove unused imports. The changes significantly improve the project's tooling for code cleanup. My review focuses on enhancing the efficiency and robustness of these new scripts. I've suggested pre-compiling regular expressions, avoiding redundant file reads, and using more reliable regex patterns to ensure the tools are fast and dependable.

[gemini-code-assist]

The current method of checking for the import statement using string containment (in) and startswith is brittle. It might fail with slight variations in whitespace (e.g., import '...') and is less clear about what it's matching. Using a single, more robust regular expression compiled once before the loop would be more efficient and reliable.

Suggested change

	changed = False
	new_lines = []
	for line in lines:
	if line.strip().startswith('import '):
	# match single or double quote
	if (f"import '{import_name}'" in line) or (f'import "{import_name}"' in line):
	changed = True
	continue # skip this line
	new_lines.append(line)
	changed = False
	new_lines = []
	# Using a regex is more robust against whitespace and quote variations.
	import_pattern = re.compile(r"^\s*import\s+(['\"])%s\1" % re.escape(import_name))
	for line in lines:
	if import_pattern.match(line):
	changed = True
	continue # skip this line
	new_lines.append(line)

[gemini-code-assist]

For improved performance and clarity, it's a good practice to pre-compile regular expressions, especially since they are used inside a loop. You can define NEEDLES as a list of compiled regex objects and then use the .search() method directly on them. This avoids compiling the same pattern repeatedly inside the file_needs_material function's loop.

Suggested change

	NEEDLES = [
	r"\bIcons\.", r"\bColors\.", r"\bElevatedButton\b", r"\bOutlinedButton\b", r"\bTextButton\b",
	]
	def file_needs_material(text: str) -> bool:
	if 'package:flutter/material.dart' in text:
	return False
	for pat in NEEDLES:
	if re.search(pat, text):
	return True
	return False
	NEEDLES = [
	re.compile(r"\bIcons\."), re.compile(r"\bColors\."), re.compile(r"\bElevatedButton\b"),
	re.compile(r"\bOutlinedButton\b"), re.compile(r"\bTextButton\b"),
	]
	def file_needs_material(text: str) -> bool:
	if 'package:flutter/material.dart' in text:
	return False
	for pat in NEEDLES:
	if pat.search(text):
	return True
	return False

[gemini-code-assist]

The main function currently reads each file to check if it needs a material import, and then add_material_import reads the same file again. This is inefficient as it results in reading each file twice. You can refactor this to read each file only once. The add_material_import function already contains the necessary logic to check and add the import, and it handles errors gracefully. Simplifying the main loop to just call add_material_import will make the code more efficient and less redundant.

def main():
    root = os.path.join(os.path.dirname(__file__), 'lib')
    changed = 0
    for dirpath, _, filenames in os.walk(root):
        for fn in filenames:
            if not fn.endswith('.dart'):
                continue
            path = os.path.join(dirpath, fn)
            # By calling add_material_import directly, we avoid reading the file twice.
            # The function itself handles the check and potential modification.
            if add_material_import(path):
                changed += 1
    print(f"Material import added to {changed} files")
    return 0