Skip to content

Commit

Permalink
Introduce scan errors and report them upon exit
Browse files Browse the repository at this point in the history
The only error for now is failing to read the code file. But the types
allow expanding on this later
  • Loading branch information
faern committed Nov 29, 2024
1 parent dbb86a9 commit e2043d1
Show file tree
Hide file tree
Showing 3 changed files with 59 additions and 15 deletions.
7 changes: 5 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ Where `[PATHS]...` is a list of files or directory to check.
### Example usage

```console
$ unicop example-files/homoglyph.js example-files/invisible.js
$ unicop example-files/homoglyph.js example-files/invisible.js example-files/not-utf-8-file.ts
? failed
× found disallowed character LATIN LETTER RETROFLEX CLICK in identifier
╭─[example-files/homoglyph.js:4:18]
Expand All @@ -71,7 +71,10 @@ $ unicop example-files/homoglyph.js example-files/invisible.js
· ╰── HANGUL JUNGSEONG FILLER
6 │ ];
╰────
Scanned 486 unicode code points in 2 files, resulting in 3 rule violations
Error while scanning example-files/not-utf-8-file.ts: Failed to read file (stream did not contain valid UTF-8)
Scanned 486 unicode code points in 2 files, resulting in:
3 rule violations
1 other error

```

Expand Down
Binary file added example-files/not-utf-8-file.ts
Binary file not shown.
67 changes: 54 additions & 13 deletions src/main.rs
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
use std::collections::HashMap;
use std::fmt;
use std::fs;
use std::io;
use std::path::{Path, PathBuf};
Expand Down Expand Up @@ -170,6 +171,7 @@ fn main() -> anyhow::Result<()> {
};

let mut num_files_scanned: u64 = 0;
let mut num_errors: u64 = 0;
let mut global_scan_stats = ScanStats {
num_unicode_code_points: 0,
num_rule_violations: 0,
Expand All @@ -181,11 +183,18 @@ fn main() -> anyhow::Result<()> {
Ok(entry) if entry.file_type().is_file() => {
let entry_path = entry.path();
dispatcher.user_config = get_user_config(entry_path)?;
if let Some(scan_stats) = check_file(&dispatcher, entry_path) {
num_files_scanned += 1;
global_scan_stats.num_unicode_code_points +=
scan_stats.num_unicode_code_points;
global_scan_stats.num_rule_violations += scan_stats.num_rule_violations;
match check_file(&dispatcher, entry_path) {
Ok(Some(scan_stats)) => {
num_files_scanned += 1;
global_scan_stats.num_unicode_code_points +=
scan_stats.num_unicode_code_points;
global_scan_stats.num_rule_violations += scan_stats.num_rule_violations;
}
Ok(None) => (),
Err(e) => {
num_errors += 1;
eprintln!("Error while scanning {}: {e}", entry_path.display());
}
}
}
Ok(_) => {}
Expand All @@ -194,25 +203,57 @@ fn main() -> anyhow::Result<()> {
}

println!(
"Scanned {} unicode code points in {} files, resulting in {} rule violations",
global_scan_stats.num_unicode_code_points,
num_files_scanned,
"Scanned {} unicode code points in {} files, resulting in:",
global_scan_stats.num_unicode_code_points, num_files_scanned,
);
println!(
"\t{} rule violations",
global_scan_stats.num_rule_violations,
);
if global_scan_stats.num_rule_violations > 0 {
match num_errors {
1 => println!("\t1 other error"),
_ => println!("\t{num_errors} other errors"),
}
if global_scan_stats.num_rule_violations > 0 || num_errors > 0 {
std::process::exit(1);
}
Ok(())
}

#[derive(Debug)]
enum ScanError {
/// Failed to read the source code file
ReadFile(io::Error),
}

impl fmt::Display for ScanError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
use ScanError::*;
match self {
ReadFile(ref e) => write!(f, "Failed to read file ({e})"),
}
}
}

impl std::error::Error for ScanError {
fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
use ScanError::*;
match &self {
ReadFile(e) => e.source(),
}
}
}

/// Scans a single file at `path` using the rules defined in `dispatcher`.
///
/// If the file was actually scanned (matched a language in the rule dispatcher),
/// then stats about the scan are returned.
fn check_file(dispatcher: &RuleDispatcher, path: &Path) -> Option<ScanStats> {
let lang = dispatcher.language(path)?;
fn check_file(dispatcher: &RuleDispatcher, path: &Path) -> Result<Option<ScanStats>, ScanError> {
let Some(lang) = dispatcher.language(path) else {
return Ok(None);
};
let filename = path.display().to_string();
let src = fs::read_to_string(path).unwrap();
let src = fs::read_to_string(path).map_err(ScanError::ReadFile)?;
let named_source = NamedSource::new(&filename, src.clone());
let mut parser = tree_sitter::Parser::new();
parser
Expand Down Expand Up @@ -275,7 +316,7 @@ fn check_file(dispatcher: &RuleDispatcher, path: &Path) -> Option<ScanStats> {
print!("{:?}", report);
}

Some(scan_stats)
Ok(Some(scan_stats))
}

/// Statistics about unicop scans.
Expand Down

0 comments on commit e2043d1

Please sign in to comment.