refactor(typos): Open up the name Parser

crate-ci · Jan 2, 2021 · 1e64080 · 1e64080
1 parent 7fdd0de
commit 1e64080
Show file tree

Hide file tree

Showing 6 changed files with 48 additions and 48 deletions.
diff --git a/benches/checks.rs b/benches/checks.rs
@@ -9,7 +9,7 @@ use typos::checks::Check;
 
 fn bench_parse_ident_str(data: &str, b: &mut test::Bencher) {
     let corrections = typos_cli::dict::BuiltIn::new(Default::default());
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     let checks = typos::checks::TyposSettings::new().build_identifier_parser();
     b.iter(|| checks.check_str(data, &parser, &corrections, &typos::report::PrintSilent));
 }
@@ -46,7 +46,7 @@ fn parse_idents_corpus_str(b: &mut test::Bencher) {
 
 fn bench_parse_ident_bytes(data: &str, b: &mut test::Bencher) {
     let corrections = typos_cli::dict::BuiltIn::new(Default::default());
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     let checks = typos::checks::TyposSettings::new().build_identifier_parser();
     b.iter(|| {
         checks.check_bytes(
@@ -90,7 +90,7 @@ fn parse_idents_corpus_bytes(b: &mut test::Bencher) {
 
 fn bench_parse_word_str(data: &str, b: &mut test::Bencher) {
     let corrections = typos_cli::dict::BuiltIn::new(Default::default());
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     let checks = typos::checks::TyposSettings::new().build_word_parser();
     b.iter(|| checks.check_str(data, &parser, &corrections, &typos::report::PrintSilent));
 }
@@ -127,7 +127,7 @@ fn parse_words_corpus(b: &mut test::Bencher) {
 
 fn bench_typos(data: &str, b: &mut test::Bencher) {
     let corrections = typos_cli::dict::BuiltIn::new(Default::default());
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     let checks = typos::checks::TyposSettings::new().build_typos();
     b.iter(|| checks.check_str(data, &parser, &corrections, &typos::report::PrintSilent));
 }
@@ -168,7 +168,7 @@ fn bench_check_file(data: &str, b: &mut test::Bencher) {
     sample_path.write_str(data).unwrap();
 
     let corrections = typos_cli::dict::BuiltIn::new(Default::default());
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     let checks = typos::checks::TyposSettings::new().build_typos();
     b.iter(|| {
         checks.check_file(

diff --git a/benches/tokenize.rs b/benches/tokenize.rs
@@ -6,39 +6,39 @@ mod data;
 
 #[bench]
 fn ident_parse_empty(b: &mut test::Bencher) {
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     b.iter(|| parser.parse_bytes(data::EMPTY.as_bytes()).last());
 }
 
 #[bench]
 fn ident_parse_no_tokens(b: &mut test::Bencher) {
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     b.iter(|| parser.parse_bytes(data::NO_TOKENS.as_bytes()).last());
 }
 
 #[bench]
 fn ident_parse_single_token(b: &mut test::Bencher) {
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     b.iter(|| {
         parser.parse_bytes(data::SINGLE_TOKEN.as_bytes()).last();
     });
 }
 
 #[bench]
 fn ident_parse_sherlock(b: &mut test::Bencher) {
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     b.iter(|| parser.parse_bytes(data::SHERLOCK.as_bytes()).last());
 }
 
 #[bench]
 fn ident_parse_code(b: &mut test::Bencher) {
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     b.iter(|| parser.parse_bytes(data::CODE.as_bytes()).last());
 }
 
 #[bench]
 fn ident_parse_corpus(b: &mut test::Bencher) {
-    let parser = typos::tokens::Parser::new();
+    let parser = typos::tokens::Tokenizer::new();
     b.iter(|| parser.parse_bytes(data::CORPUS.as_bytes()).last());
 }
 

diff --git a/crates/typos/src/checks.rs b/crates/typos/src/checks.rs
@@ -9,15 +9,15 @@ pub trait Check: Send + Sync {
     fn check_str(
         &self,
         buffer: &str,
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error>;
 
     fn check_bytes(
         &self,
         buffer: &[u8],
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error>;
@@ -31,7 +31,7 @@ pub trait Check: Send + Sync {
     fn check_filename(
         &self,
         path: &std::path::Path,
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -54,7 +54,7 @@ pub trait Check: Send + Sync {
         &self,
         path: &std::path::Path,
         explicit: bool,
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -172,7 +172,7 @@ impl Check for Typos {
     fn check_str(
         &self,
         buffer: &str,
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -217,7 +217,7 @@ impl Check for Typos {
     fn check_bytes(
         &self,
         buffer: &[u8],
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -284,7 +284,7 @@ impl Check for ParseIdentifiers {
     fn check_str(
         &self,
         buffer: &str,
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         _dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -303,7 +303,7 @@ impl Check for ParseIdentifiers {
     fn check_bytes(
         &self,
         buffer: &[u8],
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         _dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -343,7 +343,7 @@ impl Check for ParseWords {
     fn check_str(
         &self,
         buffer: &str,
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         _dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -365,7 +365,7 @@ impl Check for ParseWords {
     fn check_bytes(
         &self,
         buffer: &[u8],
-        parser: &tokens::Parser,
+        parser: &tokens::Tokenizer,
         _dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -404,7 +404,7 @@ impl Check for Files {
     fn check_str(
         &self,
         _buffer: &str,
-        _parser: &tokens::Parser,
+        _parser: &tokens::Tokenizer,
         _dictionary: &dyn Dictionary,
         _reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -414,7 +414,7 @@ impl Check for Files {
     fn check_bytes(
         &self,
         _buffer: &[u8],
-        _parser: &tokens::Parser,
+        _parser: &tokens::Tokenizer,
         _dictionary: &dyn Dictionary,
         _reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -436,7 +436,7 @@ impl Check for Files {
     fn check_filename(
         &self,
         _path: &std::path::Path,
-        _parser: &tokens::Parser,
+        _parser: &tokens::Tokenizer,
         _dictionary: &dyn Dictionary,
         _reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {
@@ -447,7 +447,7 @@ impl Check for Files {
         &self,
         path: &std::path::Path,
         _explicit: bool,
-        _parser: &tokens::Parser,
+        _parser: &tokens::Tokenizer,
         _dictionary: &dyn Dictionary,
         reporter: &dyn report::Report,
     ) -> Result<(), std::io::Error> {

diff --git a/crates/typos/src/tokens.rs b/crates/typos/src/tokens.rs
@@ -1,13 +1,13 @@
 #[derive(Debug, Clone, PartialEq, Eq, Hash)]
-pub struct ParserBuilder {
+pub struct TokenizerBuilder {
     ignore_hex: bool,
     leading_digits: bool,
     leading_chars: String,
     include_digits: bool,
     include_chars: String,
 }
 
-impl ParserBuilder {
+impl TokenizerBuilder {
     pub fn new() -> Self {
         Default::default()
     }
@@ -37,7 +37,7 @@ impl ParserBuilder {
         self
     }
 
-    pub fn build(&self) -> Parser {
+    pub fn build(&self) -> Tokenizer {
         let mut pattern = r#"\b("#.to_owned();
         Self::push_pattern(&mut pattern, self.leading_digits, &self.leading_chars);
         Self::push_pattern(&mut pattern, self.include_digits, &self.include_chars);
@@ -46,7 +46,7 @@ impl ParserBuilder {
         let words_str = regex::Regex::new(&pattern).unwrap();
         let words_bytes = regex::bytes::Regex::new(&pattern).unwrap();
 
-        Parser {
+        Tokenizer {
             words_str,
             words_bytes,
             // `leading_digits` let's us bypass the regexes since you can't have a decimal or
@@ -69,7 +69,7 @@ impl ParserBuilder {
     }
 }
 
-impl Default for ParserBuilder {
+impl Default for TokenizerBuilder {
     fn default() -> Self {
         Self {
             ignore_hex: true,
@@ -82,16 +82,16 @@ impl Default for ParserBuilder {
 }
 
 #[derive(Debug, Clone)]
-pub struct Parser {
+pub struct Tokenizer {
     words_str: regex::Regex,
     words_bytes: regex::bytes::Regex,
     ignore_numbers: bool,
     ignore_hex: bool,
 }
 
-impl Parser {
+impl Tokenizer {
     pub fn new() -> Self {
-        ParserBuilder::default().build()
+        TokenizerBuilder::default().build()
     }
 
     pub fn parse_str<'c>(&'c self, content: &'c str) -> impl Iterator<Item = Identifier<'c>> {
@@ -124,7 +124,7 @@ impl Parser {
     }
 }
 
-impl Default for Parser {
+impl Default for Tokenizer {
     fn default() -> Self {
         Self::new()
     }
@@ -387,7 +387,7 @@ mod test {
 
     #[test]
     fn tokenize_empty_is_empty() {
-        let parser = Parser::new();
+        let parser = Tokenizer::new();
 
         let input = "";
         let expected: Vec<Identifier> = vec![];
@@ -399,7 +399,7 @@ mod test {
 
     #[test]
     fn tokenize_word_is_word() {
-        let parser = Parser::new();
+        let parser = Tokenizer::new();
 
         let input = "word";
         let expected: Vec<Identifier> = vec![Identifier::new_unchecked("word", 0)];
@@ -411,7 +411,7 @@ mod test {
 
     #[test]
     fn tokenize_space_separated_words() {
-        let parser = Parser::new();
+        let parser = Tokenizer::new();
 
         let input = "A B";
         let expected: Vec<Identifier> = vec![
@@ -426,7 +426,7 @@ mod test {
 
     #[test]
     fn tokenize_dot_separated_words() {
-        let parser = Parser::new();
+        let parser = Tokenizer::new();
 
         let input = "A.B";
         let expected: Vec<Identifier> = vec![
@@ -441,7 +441,7 @@ mod test {
 
     #[test]
     fn tokenize_namespace_separated_words() {
-        let parser = Parser::new();
+        let parser = Tokenizer::new();
 
         let input = "A::B";
         let expected: Vec<Identifier> = vec![
@@ -456,7 +456,7 @@ mod test {
 
     #[test]
     fn tokenize_underscore_doesnt_separate() {
-        let parser = Parser::new();
+        let parser = Tokenizer::new();
 
         let input = "A_B";
         let expected: Vec<Identifier> = vec![Identifier::new_unchecked("A_B", 0)];
@@ -468,7 +468,7 @@ mod test {
 
     #[test]
     fn tokenize_ignore_hex_enabled() {
-        let parser = ParserBuilder::new().ignore_hex(true).build();
+        let parser = TokenizerBuilder::new().ignore_hex(true).build();
 
         let input = "Hello 0xDEADBEEF World";
         let expected: Vec<Identifier> = vec![
@@ -483,7 +483,7 @@ mod test {
 
     #[test]
     fn tokenize_ignore_hex_disabled() {
-        let parser = ParserBuilder::new()
+        let parser = TokenizerBuilder::new()
             .ignore_hex(false)
             .leading_digits(true)
             .build();
@@ -523,11 +523,11 @@ mod test {
                 &[("A", Case::Scream, 0), ("String", Case::Title, 1)],
             ),
             (
-                "SimpleXMLParser",
+                "SimpleXMLTokenizer",
                 &[
                     ("Simple", Case::Title, 0),
                     ("XML", Case::Scream, 6),
-                    ("Parser", Case::Title, 9),
+                    ("Tokenizer", Case::Title, 9),
                 ],
             ),
             (