From 51deec66d0c7fc28ac5dc7904d5ab5a64a3825ee Mon Sep 17 00:00:00 2001
From: freestrings <freestrings@gmail.com>
Date: Mon, 17 Jun 2019 15:42:46 +0900
Subject: [PATCH] escaped quote notation

---
 src/parser/mod.rs       | 36 +++++++++++++++++++++++++++++++++++-
 src/parser/tokenizer.rs | 36 ++++++++++++++++++++++++++----------
 tests/filter.rs         |  8 ++++++++
 3 files changed, 69 insertions(+), 11 deletions(-)

diff --git a/src/parser/mod.rs b/src/parser/mod.rs
index 4205ab6..16cfab5 100644
--- a/src/parser/mod.rs
+++ b/src/parser/mod.rs
@@ -4,7 +4,7 @@ pub mod parser;
 
 #[cfg(test)]
 mod parser_tests {
-    use parser::parser::{ParseToken, Parser, NodeVisitor, FilterToken};
+    use parser::parser::{FilterToken, NodeVisitor, Parser, ParseToken};
 
     struct NodeVisitorTestImpl<'a> {
         input: &'a str,
@@ -270,6 +270,20 @@ mod parser_tests {
             ParseToken::ArrayEof
         ]));
 
+        assert_eq!(run(r#"$['single\'quote']"#), Ok(vec![
+            ParseToken::Absolute,
+            ParseToken::Array,
+            ParseToken::Key("single'quote".to_string()),
+            ParseToken::ArrayEof
+        ]));
+
+        assert_eq!(run(r#"$["single\"quote"]"#), Ok(vec![
+            ParseToken::Absolute,
+            ParseToken::Array,
+            ParseToken::Key(r#"single"quote"#.to_string()),
+            ParseToken::ArrayEof
+        ]));
+
         match run("$[") {
             Ok(_) => panic!(),
             _ => {}
@@ -338,6 +352,10 @@ mod parser_tests {
 mod tokenizer_tests {
     use parser::tokenizer::{Token, TokenError, Tokenizer, TokenReader};
 
+    fn setup() {
+        let _ = env_logger::try_init();
+    }
+
     fn collect_token(input: &str) -> (Vec<Token>, Option<TokenError>) {
         let mut tokenizer = Tokenizer::new(input);
         let mut vec = vec![];
@@ -380,6 +398,8 @@ mod tokenizer_tests {
 
     #[test]
     fn token() {
+        setup();
+
         run("$.01.a",
             (
                 vec![
@@ -534,5 +554,19 @@ mod tokenizer_tests {
             Token::Split(2),
             Token::CloseArray(3)
         ], Some(TokenError::Eof)));
+
+        run(r#"$['single\'quote']"#, (vec![
+            Token::Absolute(0),
+            Token::OpenArray(1),
+            Token::SingleQuoted(2, "single\'quote".to_string()),
+            Token::CloseArray(17)
+        ], Some(TokenError::Eof)));
+
+        run(r#"$["double\"quote"]"#, (vec![
+            Token::Absolute(0),
+            Token::OpenArray(1),
+            Token::DoubleQuoted(2, "double\"quote".to_string()),
+            Token::CloseArray(17)
+        ], Some(TokenError::Eof)));
     }
 }
\ No newline at end of file
diff --git a/src/parser/tokenizer.rs b/src/parser/tokenizer.rs
index 23a3ac7..3568e08 100644
--- a/src/parser/tokenizer.rs
+++ b/src/parser/tokenizer.rs
@@ -44,8 +44,8 @@ const CH_PIPE: char = '|';
 const CH_LITTLE: char = '<';
 const CH_GREATER: char = '>';
 const CH_EXCLAMATION: char = '!';
-const CH_SINGLE_QUOTA: char = '\'';
-const CH_DOUBLE_QUOTA: char = '"';
+const CH_SINGLE_QUOTE: char = '\'';
+const CH_DOUBLE_QUOTE: char = '"';
 
 #[derive(Debug, Clone, PartialEq)]
 pub enum TokenError {
@@ -147,20 +147,36 @@ pub struct Tokenizer<'a> {
 
 impl<'a> Tokenizer<'a> {
     pub fn new(input: &'a str) -> Self {
+        trace!("input: {}", input);
         Tokenizer {
             input: PathReader::new(input),
         }
     }
 
-    fn single_quota(&mut self, pos: usize, ch: char) -> Result<Token, TokenError> {
-        let (_, val) = self.input.take_while(|c| *c != ch).map_err(to_token_error)?;
-        self.input.next_char().map_err(to_token_error)?;
+    fn quote(&mut self, ch: char) -> Result<String, TokenError> {
+        let (_, mut val) = self.input.take_while(|c| *c != ch).map_err(to_token_error)?;
+
+        if let Some('\\') = val.chars().last() {
+            self.input.next_char().map_err(to_token_error)?;
+            let _ = val.pop();
+            let (_, mut val_remain) = self.input.take_while(|c| *c != ch).map_err(to_token_error)?;
+            self.input.next_char().map_err(to_token_error)?;
+            val.push(ch);
+            val.push_str(val_remain.as_str());
+        } else {
+            self.input.next_char().map_err(to_token_error)?;
+        }
+
+        Ok(val)
+    }
+
+    fn single_quote(&mut self, pos: usize, ch: char) -> Result<Token, TokenError> {
+        let val = self.quote(ch)?;
         Ok(Token::SingleQuoted(pos, val))
     }
 
-    fn double_quota(&mut self, pos: usize, ch: char) -> Result<Token, TokenError> {
-        let (_, val) = self.input.take_while(|c| *c != ch).map_err(to_token_error)?;
-        self.input.next_char().map_err(to_token_error)?;
+    fn double_quote(&mut self, pos: usize, ch: char) -> Result<Token, TokenError> {
+        let val = self.quote(ch)?;
         Ok(Token::DoubleQuoted(pos, val))
     }
 
@@ -259,8 +275,8 @@ impl<'a> Tokenizer<'a> {
             Some(t) => Ok(t),
             None => {
                 match ch {
-                    CH_SINGLE_QUOTA => self.single_quota(pos, ch),
-                    CH_DOUBLE_QUOTA => self.double_quota(pos, ch),
+                    CH_SINGLE_QUOTE => self.single_quote(pos, ch),
+                    CH_DOUBLE_QUOTE => self.double_quote(pos, ch),
                     CH_EQUAL => self.equal(pos, ch),
                     CH_GREATER => self.greater(pos, ch),
                     CH_LITTLE => self.little(pos, ch),
diff --git a/tests/filter.rs b/tests/filter.rs
index 1b0fb18..aa56e13 100644
--- a/tests/filter.rs
+++ b/tests/filter.rs
@@ -356,4 +356,12 @@ fn empty_range() {
     setup();
 
     select_and_then_compare("$[:]", json!(["first", "second"]), json!(["first", "second"]));
+}
+
+#[test]
+fn quote() {
+    setup();
+
+    select_and_then_compare(r#"$['single\'quote']"#, json!({"single'quote":"value"}), json!(["value"]));
+    select_and_then_compare(r#"$["double\"quote"]"#, json!({"double\"quote":"value"}), json!(["value"]));
 }
\ No newline at end of file