nyx/src/utils/project.rs

63 lines
1.9 KiB
Rust
Raw Normal View History

use crate::errors::{NyxError, NyxResult};
use std::path::{Path, PathBuf};
/// Determine `<project-name, path/to/<project>.sqlite>`.
pub fn get_project_info(project_path: &Path, config_dir: &Path) -> NyxResult<(String, PathBuf)> {
let project_name = project_path
.file_name()
.and_then(|n| n.to_str())
.ok_or_else(|| NyxError::Other("Unable to determine project name".into()))?;
let db_name = sanitize_project_name(project_name);
Added experimental control flow analysis and syntax classification for rust lang (#22) * Introduce control flow graph (CFG) support: - Added `cfg.rs` with CFG generation and analysis utilities. - Integrated `petgraph` library for graph-based computations. - Updated `ast.rs` to utilize CFG for function analysis. - Modified `Cargo.toml` and `Cargo.lock` to include new dependencies. - Improved static analysis with taint tracking through CFG paths. * feat: enhance control flow analysis with taint tracking and node labeling * feat: improve control flow graph with enhanced node handling and new tests * Remove unnecessary reference marker in `byte_offset_to_point` comment. * Remove unnecessary reference marker in `byte_offset_to_point` comment. * Refactor `ast.rs` for performance and clarity; enhance `cfg.rs` with recursive CFG generation and improved classification logic for AST analysis. * Refactor CFG and taint tracking logic: - Enhanced `cfg.rs` with inline helper function `text_of` for cleaner UTF-8 handling in AST nodes. - Expanded `labels.rs` rules with detailed `Sources`, `Sanitizers`, and `Sinks` for improved classification. - Refined `push_node` to handle method call expressions with object-function pairing. - Simplified code handling in trivia skipping and debug-only logic. * Enhance `cfg.rs` with `first_call_ident` helper and improve identifier extraction logic in `push_node`. * Add targeted CFG taint-tracking tests to enhance analysis coverage. * Enhance CFG generation with loop expression handling and improve taint tracking logic. Add new sanitization example in `examples/sanitize/example.rs`. * Update README with installation instructions for Cargo and GitHub releases. * Expand taint-tracking with precise `def-use` computation and enhance `labels.rs` for detailed classification. Extend `examples/sanitize` with realistic scenarios demonstrating new rules. * Refactor `labels.rs`: - Removed redundant `LabelRule` entries for cleaner rule definitions. - Adjusted matching logic to prioritize suffix and prefix matches effectively. * Refactor `labels.rs`: - Removed redundant `LabelRule` entries for cleaner rule definitions. - Adjusted matching logic to prioritize suffix and prefix matches effectively. * Add test for taint tracking with multiple sources in `cfg.rs`. * Add `function_summaries` table and implement summary upsert/load methods. Refactor to handle summary storage and retrieval efficiently, with placeholder clean/drop logic. * refactor: split `labels.rs` into modular structure with language-specific files * refactor: split `labels.rs` into modular structure with language-specific files * refactor: clean up SQL table definitions in `database.rs` for better readability * refactor: simplify CFG structure by removing lifetime parameters and enhancing taint metadata handling * refactor: update TODO comments in `cfg.rs` to clarify future enhancements for cap labels and function details * refactor: remove redundant header from README.md for improved clarity * feat: add PHF-based syntax classifiers and Kind enum for efficient syntax mapping across languages * feat: introduce analysis modes for enhanced scanner configuration and diagnostics * feat: define Kind enum for syntax classification in control flow analysis * feat: bump version to 0.2.0-alpha and update CHANGELOG for new features and fixes * refactor: clean up imports and formatting in AST and CFG modules for improved readability * refactor: simplify function signatures and improve code readability in CFG and module files * fix: correct rayon_thread_stack_size comment to reflect actual value of 8 MiB * refactor: update string formatting in clean and project modules for consistency * refactor: fix indentation in clean.rs for improved readability --------- Co-authored-by: elipeter <eli.peter@es.fcm.travel>
2025-06-28 17:36:14 +02:00
let db_path = config_dir.join(format!("{db_name}.sqlite"));
Ok((project_name.to_owned(), db_path))
}
pub fn sanitize_project_name(name: &str) -> String {
name.to_lowercase()
.chars()
.map(|c| match c {
' ' | '\t' | '\n' | '\r' => '_',
c if c.is_alphanumeric() || c == '_' || c == '-' => c,
_ => '_',
})
.collect::<String>()
.split('_')
.filter(|s| !s.is_empty())
.collect::<Vec<_>>()
.join("_")
}
#[test]
fn sanitize_project_name_is_idempotent_and_lossless_enough() {
let samples = [
("My Project", "my_project"),
("Hello-World", "hello-world"),
("mixed_case", "mixed_case"),
("tabs\tspaces\n", "tabs_spaces"),
(" multiple ", "multiple"),
("weird@$*chars", "weird_chars"),
];
for (input, expected) in samples {
Added experimental control flow analysis and syntax classification for rust lang (#22) * Introduce control flow graph (CFG) support: - Added `cfg.rs` with CFG generation and analysis utilities. - Integrated `petgraph` library for graph-based computations. - Updated `ast.rs` to utilize CFG for function analysis. - Modified `Cargo.toml` and `Cargo.lock` to include new dependencies. - Improved static analysis with taint tracking through CFG paths. * feat: enhance control flow analysis with taint tracking and node labeling * feat: improve control flow graph with enhanced node handling and new tests * Remove unnecessary reference marker in `byte_offset_to_point` comment. * Remove unnecessary reference marker in `byte_offset_to_point` comment. * Refactor `ast.rs` for performance and clarity; enhance `cfg.rs` with recursive CFG generation and improved classification logic for AST analysis. * Refactor CFG and taint tracking logic: - Enhanced `cfg.rs` with inline helper function `text_of` for cleaner UTF-8 handling in AST nodes. - Expanded `labels.rs` rules with detailed `Sources`, `Sanitizers`, and `Sinks` for improved classification. - Refined `push_node` to handle method call expressions with object-function pairing. - Simplified code handling in trivia skipping and debug-only logic. * Enhance `cfg.rs` with `first_call_ident` helper and improve identifier extraction logic in `push_node`. * Add targeted CFG taint-tracking tests to enhance analysis coverage. * Enhance CFG generation with loop expression handling and improve taint tracking logic. Add new sanitization example in `examples/sanitize/example.rs`. * Update README with installation instructions for Cargo and GitHub releases. * Expand taint-tracking with precise `def-use` computation and enhance `labels.rs` for detailed classification. Extend `examples/sanitize` with realistic scenarios demonstrating new rules. * Refactor `labels.rs`: - Removed redundant `LabelRule` entries for cleaner rule definitions. - Adjusted matching logic to prioritize suffix and prefix matches effectively. * Refactor `labels.rs`: - Removed redundant `LabelRule` entries for cleaner rule definitions. - Adjusted matching logic to prioritize suffix and prefix matches effectively. * Add test for taint tracking with multiple sources in `cfg.rs`. * Add `function_summaries` table and implement summary upsert/load methods. Refactor to handle summary storage and retrieval efficiently, with placeholder clean/drop logic. * refactor: split `labels.rs` into modular structure with language-specific files * refactor: split `labels.rs` into modular structure with language-specific files * refactor: clean up SQL table definitions in `database.rs` for better readability * refactor: simplify CFG structure by removing lifetime parameters and enhancing taint metadata handling * refactor: update TODO comments in `cfg.rs` to clarify future enhancements for cap labels and function details * refactor: remove redundant header from README.md for improved clarity * feat: add PHF-based syntax classifiers and Kind enum for efficient syntax mapping across languages * feat: introduce analysis modes for enhanced scanner configuration and diagnostics * feat: define Kind enum for syntax classification in control flow analysis * feat: bump version to 0.2.0-alpha and update CHANGELOG for new features and fixes * refactor: clean up imports and formatting in AST and CFG modules for improved readability * refactor: simplify function signatures and improve code readability in CFG and module files * fix: correct rayon_thread_stack_size comment to reflect actual value of 8 MiB * refactor: update string formatting in clean and project modules for consistency * refactor: fix indentation in clean.rs for improved readability --------- Co-authored-by: elipeter <eli.peter@es.fcm.travel>
2025-06-28 17:36:14 +02:00
assert_eq!(sanitize_project_name(input), expected, "input: {input}");
assert_eq!(sanitize_project_name(expected), expected);
}
}
#[test]
fn get_project_info_uses_sanitized_name_in_sqlite_path() {
let tmp = tempfile::tempdir().unwrap();
let root = tmp.path();
let project_dir = root.join("Example Project");
std::fs::create_dir(&project_dir).unwrap();
let (project_name, db_path) =
get_project_info(&project_dir, root).expect("should detect project");
assert_eq!(project_name, "Example Project");
assert_eq!(db_path, root.join("example_project.sqlite"));
}