Skip to content
This repository was archived by the owner on Jun 6, 2018. It is now read-only.

Added Unicode category support #11

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Added Unicode category support #11

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1b21377
Added Unicode category support.
cmkilger Jun 6, 2015
e6741a0
Added non-Unicode category support.
cmkilger Jun 6, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 28 additions & 0 deletions src/js/parser/javascript/escape.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,28 @@ function hex(value) {
return `(0x${str})`;
}

function unicodeProperty(arg) {
var map = {
'L': 'Letter', 'Ll': 'Lowercase_Letter', 'Lu': 'Uppercase_Letter', 'Lt': 'Titlecase_Letter',
'L&': 'Cased_Letter', 'Lm': 'Modifier_Letter', 'Lo': 'Other_Letter', 'M': 'Mark', 'Mn': 'Non_Spacing_Mark',
'Mc': 'Spacing_Combining_Mark', 'Me': 'Enclosing_Mark', 'Z': 'Separator', 'Zs': 'Space_Separator',
'Zl': 'Line_Separator', 'Zp': 'Paragraph_Separator', 'S': 'Symbol', 'Sm': 'Math_Symbol',
'Sc': 'Currency_Symbol', 'Sk': 'Modifier_Symbol', 'So': 'Other_Symbol', 'N': 'Number',
'Nd': 'Decimal_Digit_Number', 'Nl': 'Letter_Number', 'No': 'Other_Number', 'P': 'Punctuation',
'Pd': 'Dash_Punctuation', 'Ps': 'Open_Punctuation', 'Pe': 'Close_Punctuation', 'Pi': 'Initial_Punctuation',
'Pf': 'Final_Punctuation', 'Pc': 'Connector_Punctuation', 'Po': 'Other_Punctuation', 'C': 'Other',
'Cc': 'Control', 'Cf': 'Format', 'Co': 'Private_Use', 'Cs': 'Surrogate', 'Cn': 'Unassigned'
};
var temp = map[arg];
if (temp) {
arg = temp;
}
if (arg.slice(0, 2) == 'In') {
arg = 'in '+arg.slice(2);
}
return arg.replace(/_/g, ' ');
}

export default {
type: 'escape',

Expand Down Expand Up @@ -84,5 +106,11 @@ export default {
},
u() {
return [`U+${this.arg.toUpperCase()}`, parseInt(this.arg, 16), false];
},
p() {
return [unicodeProperty(this.arg), -1, false];
},
P() {
return ['non-'+unicodeProperty(this.arg), -1, false];
}
};
14 changes: 11 additions & 3 deletions src/js/parser/javascript/grammar.peg
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,14 +25,18 @@ grammar JavascriptRegexp
/ octal_escape
/ hex_escape
/ unicode_escape
/ null_escape )
/ null_escape
/ unicode_category_escape
/ non_unicode_category_escape )
charset_range_escape <- "\\" esc:(
code:[bfnrtv] arg:""?
/ control_escape
/ octal_escape
/ hex_escape
/ unicode_escape
/ null_escape )
/ null_escape
/ unicode_category_escape
/ non_unicode_category_escape )
charset_literal <- ( ""? literal:[^\\\]] )
/ ( literal:"\\" &"c" )
/ ( "\\" literal:[^bdDfnrsStvwW] )
Expand All @@ -45,7 +49,9 @@ grammar JavascriptRegexp
/ octal_escape
/ hex_escape
/ unicode_escape
/ null_escape )
/ null_escape
/ unicode_category_escape
/ non_unicode_category_escape )
literal <- ( ""? literal:[^|\\/.\[\(\)?+*$^] )
/ ( literal:"\\" &"c" )
/ ( "\\" literal:. )
Expand All @@ -55,3 +61,5 @@ grammar JavascriptRegexp
hex_escape <- code:"x" arg:( [0-9a-fA-F] [0-9a-fA-F] )
unicode_escape <- code:"u" arg:( [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] )
null_escape <- code:"0" arg:""?
unicode_category_escape <- code:"p" "{" arg:([_0-9a-zA-Z-]+) "}"
non_unicode_category_escape <- code:"P" "{" arg:([_0-9a-zA-Z-]+) "}"