Merge pull request #10 from frederikstroem/release-v0.4.0

v0.4.0

CHANGELOG.md

@@ -10,8 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Add merge CI/CD to verify Git tags, Cargo.toml version, CHANGELOG.md version and PKGBUILD version
 - Add printing of pathing relative to home directory (if applicable)
 - Add printing of pathing relative to root directory
-- Include only files matching a regex
-- Exclude files matching a regex
+- Exclude files matching a glob pattern
 - Add tests
 - Add `cargo test` CI/CD
 - Make async
@@ -29,6 +28,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Add video/gif demo to README.md
 - Improve code quality and structure
 
+## [v0.4.0] - 2024-01-26
+
+### Added
+- Support for excluding files and directories matching specified glob patterns with the new `-e` or `--exclude` option.
+- Clarification on the usage of glob patterns as part of the known issues in `README.md`.
+
+### Fixed
+- Prevention of repeated prints of the same file by incorporating a HashSet to track already processed files in the `FileWalker`.
+
+### Changed
+- Updated the `psource --help` output in `README.md` to reflect the new `-e` or `--exclude` option.
+- Updated the Unreleased section in `CHANGELOG.md` to reflect the new `-e` or `--exclude` option.
+
 ## [v0.3.1] - 2024-01-16
 
 ### Fixed

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "psource"
-version = "0.3.1"
+version = "0.4.0"
 authors = ["Frederik Holm Strøm <crates.io@frederikstroem.com>"]
 description = "CLI tool to pretty print source code to stdout or directly to the clipboard."
 edition = "2021"
@@ -20,3 +20,4 @@ walkdir = "2.4.0"
 arboard = "3.3.0"
 file-format = "0.23.0"
 git2 = "0.18"
+glob = "0.3.1"

README.md

@@ -76,6 +76,7 @@ Options:
   -c, --copy                 Copy the source code to the clipboard
   -a, --ancestry <ANCESTRY>  Display the file's ancestry in the output path by including the specified number of parent directories relative to the current working directory, or 0 to omit the ancestry [default: 1]
   -g, --git-ancestry         Display the file's ancestry in the output path, including parent directories from the current working directory within a Git repository to its root, unlike the fixed number specified by the 'ancestry' option
+  -e, --exclude <EXCLUDE>    Exclude files and directories matching the specified glob pattern
   -h, --help                 Print help
   -V, --version              Print version
 ```
@@ -151,7 +152,13 @@ The LLM should be able to help you complete the task.
 
 **Tip:** A file tree structure can sometimes help the LLM to better understand the context of the code. For such a task, I recommend using [eza](https://github.com/eza-community/eza) with the `--tree` option. To pipe it to the clipboard, a tool like [xsel](https://github.com/kfish/xsel) can be used, e.g., `eza --tree | xsel -b`.
 
-
 ## Known issues
 ### Speeding up the copy to clipboard process
 Due to a bug in the software supply chain, the `-c` option requires psource to wait for some time before exiting, else the clipboard will not be updated on some systems (discovered on KDE Plasma running X11).[[1]](https://github.com/1Password/arboard/issues/114)[[2]](https://github.com/sigoden/aichat/issues/160) To speed up the process, the `psource` stdout can be piped to a clipboard tool like [xsel](https://github.com/kfish/xsel), e.g., `psource src | xsel -b`.
+
+### Exclude option not working
+The exclude option has some rough edges right now and future improvements are planned.
+
+If the `*` exclude patterns are not working as excepted, try to quote the pattern, e.g., `psource Cargo.toml README.md -e 'Cargo*'`
+
+If you need to exclude a file within a subdirectory, consider using a glob pattern such as `psource src -e '*/main.rs'` to target `main.rs` in any immediate subdirectory, or `psource src -e '**/main.rs'` to match all `main.rs` files across all levels of subdirectories.

src/cli/cli.rs

@@ -20,13 +20,9 @@ pub struct Cli {
     #[arg(short, long = "git-ancestry", conflicts_with = "ancestry")]
     pub git_ancestry: bool,
 
-    // /// Exclude files matching the given regex
-    // #[arg(short, long)]
-    // pub exclude: Option<String>,
-
-    // /// Include only files matching the given regex
-    // #[arg(short, long)]
-    // pub include: Option<String>,
+    /// Exclude files and directories matching the specified glob pattern
+    #[arg(short, long, action = clap::ArgAction::Append)]
+    pub exclude: Vec<String>,
 
     /// Input files and directories
     #[arg(required = true)]

src/printer/file_walker.rs

@@ -1,28 +1,58 @@
 use walkdir::WalkDir;
 use std::path::{Path, PathBuf};
 use file_format::{FileFormat, Kind};
+use glob::Pattern;
+use std::collections::HashSet;
 
-pub struct FileWalker {}
+pub struct FileWalker {
+    exclude_patterns: Vec<Pattern>,
+}
 
 impl FileWalker {
-    pub fn new() -> Self {
-        FileWalker {}
+    pub fn new(exclude_patterns: Vec<String>) -> Self {
+        let exclude_patterns = exclude_patterns
+            .into_iter()
+            .map(|p| Pattern::new(&p).expect("Failed to create glob pattern"))
+            .collect();
+        FileWalker { exclude_patterns }
     }
 
     pub fn walk(&self, input_paths: &[String]) -> anyhow::Result<Vec<PathBuf>> {
-        let mut paths = Vec::new();
-        for input_path in input_paths {
-            for entry in WalkDir::new(input_path) {
-                let entry = entry?;
-                if entry.file_type().is_file() {
-                    // TODO: Add filtering logic (exclude/include) based on regex.
-                    if !self.is_binary(&entry.path()) {
-                        paths.push(entry.into_path());
+        let mut unique_paths = HashSet::new(); // To store unique paths
+        let mut final_paths = Vec::new(); // Final list of paths to return
+
+        for input_str in input_paths {
+            let input_path = Path::new(input_str);
+
+            // Skip if this path is excluded
+            if self.is_excluded(input_path) {
+                continue;
+            }
+
+            // Process directories and files differently
+            if input_path.is_dir() {
+                for entry in WalkDir::new(input_path) {
+                    let entry = entry?;
+                    let path = entry.path();
+
+                    // Skip if the path is excluded or is a directory
+                    if self.is_excluded(path) || entry.file_type().is_dir() {
+                        continue;
                     }
+
+                    // If the file is not binary and not already included, add it to the list
+                    if !self.is_binary(path) && unique_paths.insert(path.to_path_buf()) {
+                        final_paths.push(path.to_path_buf());
+                    }
+                }
+            } else if input_path.is_file() {
+                // If it's a single file, add it if it's not binary and not already included
+                if !self.is_binary(input_path) && unique_paths.insert(input_path.to_path_buf()) {
+                    final_paths.push(input_path.to_path_buf());
                 }
             }
         }
-        Ok(paths)
+        Ok(final_paths)
     }
 
     fn is_binary(&self, path: &Path) -> bool {
@@ -37,4 +67,8 @@ impl FileWalker {
             true
         }
     }
+
+    fn is_excluded(&self, path: &Path) -> bool {
+        self.exclude_patterns.iter().any(|pattern| pattern.matches_path(path))
+    }
 }

src/printer/printer.rs

@@ -22,7 +22,7 @@ impl<'a> Printer<'a> {
             Self {
                 cli,
                 config,
-                file_walker: FileWalker::new(),
+                file_walker: FileWalker::new(cli.exclude.clone()),
             }
         )
     }