...
This commit is contained in:
98
src/text/fix.rs
Normal file
98
src/text/fix.rs
Normal file
@@ -0,0 +1,98 @@
|
||||
|
||||
|
||||
pub fn name_fix(text: &str) -> String {
|
||||
let mut result = String::with_capacity(text.len());
|
||||
|
||||
let mut last_was_underscore = false;
|
||||
for c in text.chars() {
|
||||
// Keep only ASCII characters
|
||||
if c.is_ascii() {
|
||||
// Replace specific characters with underscore
|
||||
if c.is_whitespace() || c == ',' || c == '-' || c == '"' || c == '\'' ||
|
||||
c == '#' || c == '!' || c == '(' || c == ')' || c == '[' || c == ']' ||
|
||||
c == '=' || c == '+' || c == '<' || c == '>' {
|
||||
// Only add underscore if the last character wasn't an underscore
|
||||
if !last_was_underscore {
|
||||
result.push('_');
|
||||
last_was_underscore = true;
|
||||
}
|
||||
} else {
|
||||
// Add the character as is (will be converted to lowercase later)
|
||||
result.push(c);
|
||||
last_was_underscore = false;
|
||||
}
|
||||
}
|
||||
// Non-ASCII characters are simply skipped
|
||||
}
|
||||
|
||||
// Convert to lowercase
|
||||
return result.to_lowercase();
|
||||
}
|
||||
|
||||
pub fn path_fix(text: &str) -> String {
|
||||
// If path ends with '/', return as is
|
||||
if text.ends_with('/') {
|
||||
return text.to_string();
|
||||
}
|
||||
|
||||
// Find the last '/' to extract the filename part
|
||||
match text.rfind('/') {
|
||||
Some(pos) => {
|
||||
// Extract the path and filename parts
|
||||
let path = &text[..=pos];
|
||||
let filename = &text[pos+1..];
|
||||
|
||||
// Apply name_fix to the filename part only
|
||||
return format!("{}{}", path, name_fix(filename));
|
||||
},
|
||||
None => {
|
||||
// No '/' found, so the entire text is a filename
|
||||
return name_fix(text);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn test_name_fix() {
|
||||
// Test ASCII conversion and special character replacement
|
||||
assert_eq!(name_fix("Hello World"), "hello_world");
|
||||
assert_eq!(name_fix("File-Name.txt"), "file_name.txt");
|
||||
assert_eq!(name_fix("Test!@#$%^&*()"), "test_");
|
||||
assert_eq!(name_fix("Space, Tab\t, Comma,"), "space_tab_comma_");
|
||||
assert_eq!(name_fix("Quotes\"'"), "quotes_");
|
||||
assert_eq!(name_fix("Brackets[]<>"), "brackets_");
|
||||
assert_eq!(name_fix("Operators=+-"), "operators_");
|
||||
|
||||
// Test non-ASCII characters removal
|
||||
assert_eq!(name_fix("Café"), "caf");
|
||||
assert_eq!(name_fix("Résumé"), "rsum");
|
||||
assert_eq!(name_fix("Über"), "ber");
|
||||
|
||||
// Test lowercase conversion
|
||||
assert_eq!(name_fix("UPPERCASE"), "uppercase");
|
||||
assert_eq!(name_fix("MixedCase"), "mixedcase");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_path_fix() {
|
||||
// Test path ending with /
|
||||
assert_eq!(path_fix("/path/to/directory/"), "/path/to/directory/");
|
||||
|
||||
// Test single filename
|
||||
assert_eq!(path_fix("filename.txt"), "filename.txt");
|
||||
assert_eq!(path_fix("UPPER-file.md"), "upper_file.md");
|
||||
|
||||
// Test path with filename
|
||||
assert_eq!(path_fix("/path/to/File Name.txt"), "/path/to/file_name.txt");
|
||||
assert_eq!(path_fix("./relative/path/to/DOCUMENT-123.pdf"), "./relative/path/to/document_123.pdf");
|
||||
assert_eq!(path_fix("/absolute/path/to/Résumé.doc"), "/absolute/path/to/rsum.doc");
|
||||
|
||||
// Test path with special characters in filename
|
||||
assert_eq!(path_fix("/path/with/[special]<chars>.txt"), "/path/with/_special_chars_.txt");
|
||||
}
|
||||
}
|
||||
|
@@ -1 +1,5 @@
|
||||
use text::*;
|
||||
mod dedent;
|
||||
mod fix;
|
||||
|
||||
pub use dedent::*;
|
||||
pub use fix::*;
|
Reference in New Issue
Block a user