Beginning to add some functionality to the parser

2014-11-26 18:24:40 -05:00
parent c6f2271867
commit facb99e8bc
6 changed files with 70 additions and 7 deletions
@@ -0,0 +1,85 @@
+grammar JavascriptRegexp
+  root <- ( ( "/" regexp "/" fl:[igm]* ) / regexp ) <Root>
+  regexp <- match ( "|" regexp )? <Regexp>
+  match <- anchor_start? ( ( subexp / charset / terminal ) repeat? )* anchor_end?
+  anchor_start <- "^"
+  anchor_end <- "$"
+  repeat <- ( repeat_any / repeat_required / repeat_optional / repeat_spec ) repeat_greedy?
+  repeat_any <- "*"
+  repeat_required <- "+"
+  repeat_optional <- "?"
+  repeat_spec <- "{" [0-9]+ "," [0-9]+ "}"
+               / "{," [0-9]+ "}"
+               / "{" [0-9]+ ",}"
+               / "{" [0-9]+ "}"
+  repeat_greedy <- "?"
+  subexp <- "(" ( subexp_no_capture / subexp_positive_lookahead / subexp_negative_lookahead )? regexp ")"
+  subexp_no_capture <- "?:"
+  subexp_positive_lookahead <- "?="
+  subexp_negative_lookahead <- "?!"
+  charset <- "[" "^"? ( charset_range / charset_terminal )* "]"
+  charset_range <- charset_terminal "-" charset_terminal
+  charset_terminal <- charset_escape / charset_literal
+  charset_escape <- ( backspace_esc
+                    / control_esc
+                    / digit_esc
+                    / non_digit_esc
+                    / form_feed_esc
+                    / line_feed_esc
+                    / carriage_return_esc
+                    / white_space_esc
+                    / non_white_space_esc
+                    / tab_esc
+                    / vertical_tab_esc
+                    / word_esc
+                    / non_word_esc
+                    / octal_esc
+                    / hex_esc
+                    / unicode_esc
+                    / null_esc
+                    / literal_esc )
+  charset_literal <- [^\\\]]
+  terminal <- any_character / escape / literal
+  any_character <- "."
+  escape <- ( word_boundary_esc
+            / non_word_boundary_esc
+            / control_esc
+            / digit_esc
+            / non_digit_esc
+            / form_feed_esc
+            / line_feed_esc
+            / carriage_return_esc
+            / white_space_esc
+            / non_white_space_esc
+            / tab_esc
+            / vertical_tab_esc
+            / word_esc
+            / non_word_esc
+            / back_reference
+            / octal_esc
+            / hex_esc
+            / unicode_esc
+            / null_esc
+            / literal_esc )
+  literal <- [^|\\/.\[\(\)?+*$^]
+  back_reference <- "\\" [1-9]
+  word_boundary_esc <- "\\b"
+  non_word_boundary_esc <- "\\B"
+  backspace_esc <- "\\b"
+  control_esc <- "\\b" .
+  digit_esc <- "\\d"
+  non_digit_esc <- "\\D"
+  form_feed_esc <- "\\f"
+  line_feed_esc <- "\\n"
+  carriage_return_esc <- "\\r"
+  white_space_esc <- "\\s"
+  non_white_space_esc <- "\\S"
+  tab_esc <- "\\t"
+  vertical_tab_esc <- "\\v"
+  word_esc <- "\\w"
+  non_word_esc <- "\\W"
+  octal_esc <- "\\0" [0-7]+
+  hex_esc <- "\\x" [0-9a-fA-F] [0-9a-fA-F]
+  unicode_esc <- "\\u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]
+  null_esc <- "\\0"
+  literal_esc <- "\\" .
@@ -0,0 +1,9 @@
+export default {
+  matches() {
+    if (this.elements[1].regexp) {
+      return [this.match].concat(this.elements[1].regexp.matches());
+    } else {
+      return [this.match];
+    }
+  }
+};
@@ -0,0 +1,25 @@
+export default {
+  flags() {
+    var flags;
+
+    if (this.fl) {
+      flags = this.fl.textValue;
+    } else {
+      flags = '';
+    }
+
+    return {
+      global: /g/.test(flags),
+      ignore_case: /i/.test(flags),
+      multiline: /m/.test(flags)
+    };
+  },
+
+  expression() {
+    if (this.regexp) {
+      return this.regexp;
+    } else {
+      return this;
+    }
+  }
+};