Skip to content

Anchor at beginning of numbers #43

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
nobu merged 7 commits into from
Feb 25, 2022
Merged

Anchor at beginning of numbers #43

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
8393a0e
Extracted common leading pattern
nobu Jul 8, 2021
06301af
Use possessive match
nobu Jul 8, 2021
76656a1
Separate era from preceding word
nobu Jul 8, 2021
c47ca7a
Anchor at beginning of numbers
nobu Jul 8, 2021
782286a
Anchor at beginning of numbers
nobu Jul 8, 2021
72da893
Update tests
nobu Nov 24, 2021
2c00fce
Scale timeouts
nobu Nov 24, 2021
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
59 changes: 36 additions & 23 deletions ext/date/date_parse.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -253,6 +253,8 @@ s3e(VALUE hash, VALUE y, VALUE m, VALUE d, int bc)
#define ABBR_DAYS "sun|mon|tue|wed|thu|fri|sat"
#define ABBR_MONTHS "jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec"

#define NUMBER "(?<!\\d)\\d"

#ifdef TIGHT_PARSER
#define VALID_DAYS "(?:" DAYS ")" "|(?:tues|wednes|thurs|thur|" ABBR_DAYS ")\\.?"
#define VALID_MONTHS "(?:" MONTHS ")" "|(?:sept|" ABBR_MONTHS ")\\.?"
Expand Down Expand Up @@ -652,24 +654,27 @@ parse_time(VALUE str, VALUE hash)
{
static const char pat_source[] =
"("
"" NUMBER "+\\s*"
"(?:"
"\\d+\\s*:\\s*\\d+"
"(?:"
":\\s*\\d+"
"(?:"
#ifndef TIGHT_PARSER
"\\s*:\\s*\\d+(?:[,.]\\d*)?"
"\\s*:\\s*\\d+(?:[,.]\\d*)?"
#else
"\\s*:\\s*\\d+(?:[,.]\\d+)?"
"\\s*:\\s*\\d+(?:[,.]\\d+)?"
#endif
")?"
"|"
"h(?:\\s*\\d+m?(?:\\s*\\d+s?)?)?"
")"
"(?:"
"\\s*"
"[ap](?:m\\b|\\.m\\.)"
")?"
"|"
"\\d+\\s*h(?:\\s*\\d+m?(?:\\s*\\d+s?)?)?"
")"
"(?:"
"\\s*"
"[ap](?:m\\b|\\.m\\.)"
")?"
"|"
"\\d+\\s*[ap](?:m\\b|\\.m\\.)"
")"
")"
"(?:"
"\\s*"
Expand All @@ -691,6 +696,9 @@ parse_time(VALUE str, VALUE hash)
#endif
}

#define BEGIN_ERA "\\b"
#define END_ERA "(?!(?<!\\.)[a-z])"

#ifdef TIGHT_PARSER
static int
parse_era1_cb(VALUE m, VALUE hash)
Expand All @@ -702,7 +710,7 @@ static int
parse_era1(VALUE str, VALUE hash)
{
static const char pat_source[] =
"(a(?:d|\\.d\\.))";
BEGIN_ERA "(a(?:d\\b|\\.d\\.))" END_ERA;
static VALUE pat = Qnil;

REGCOMP_I(pat);
Expand All @@ -724,8 +732,9 @@ parse_era2_cb(VALUE m, VALUE hash)
static int
parse_era2(VALUE str, VALUE hash)
{
static const char pat_source[] =
"(c(?:e|\\.e\\.)|b(?:ce|\\.c\\.e\\.)|b(?:c|\\.c\\.))";
static const char pat_source[] = BEGIN_ERA
"(c(?:e\\b|\\.e\\.)|b(?:ce\\b|\\.c\\.e\\.)|b(?:c\\b|\\.c\\.))"
END_ERA;
static VALUE pat = Qnil;

REGCOMP_I(pat);
Expand Down Expand Up @@ -829,7 +838,7 @@ parse_eu(VALUE str, VALUE hash)
FPW_COM FPT_COM
#endif
#ifndef TIGHT_PARSER
"('?\\d+)[^-\\d\\s]*"
"('?" NUMBER "+)[^-\\d\\s]*"
#else
"(\\d+)(?:(?:st|nd|rd|th)\\b)?"
#endif
Expand All @@ -842,7 +851,11 @@ parse_eu(VALUE str, VALUE hash)
"(?:"
"\\s*"
#ifndef TIGHT_PARSER
"(c(?:e|\\.e\\.)|b(?:ce|\\.c\\.e\\.)|a(?:d|\\.d\\.)|b(?:c|\\.c\\.))?"
"(?:"
BEGIN_ERA
"(c(?:e|\\.e\\.)|b(?:ce|\\.c\\.e\\.)|a(?:d|\\.d\\.)|b(?:c|\\.c\\.))"
END_ERA
")?"
"\\s*"
"('?-?\\d+(?:(?:st|nd|rd|th)\\b)?)"
#else
Expand Down Expand Up @@ -919,8 +932,8 @@ parse_us(VALUE str, VALUE hash)
COM_FPT
#endif
"(?:"
"\\s*,?"
"\\s*"
"\\s*+,?"
"\\s*+"
#ifndef TIGHT_PARSER
"(c(?:e|\\.e\\.)|b(?:ce|\\.c\\.e\\.)|a(?:d|\\.d\\.)|b(?:c|\\.c\\.))?"
"\\s*"
Expand Down Expand Up @@ -967,7 +980,7 @@ parse_iso(VALUE str, VALUE hash)
{
static const char pat_source[] =
#ifndef TIGHT_PARSER
"('?[-+]?\\d+)-(\\d+)-('?-?\\d+)"
"('?[-+]?" NUMBER "+)-(\\d+)-('?-?\\d+)"
#else
BOS
FPW_COM FPT_COM
Expand Down Expand Up @@ -1321,7 +1334,7 @@ parse_vms11(VALUE str, VALUE hash)
{
static const char pat_source[] =
#ifndef TIGHT_PARSER
"('?-?\\d+)-(" ABBR_MONTHS ")[^-/.]*"
"('?-?" NUMBER "+)-(" ABBR_MONTHS ")[^-/.]*"
"-('?-?\\d+)"
#else
BOS
Expand Down Expand Up @@ -1416,7 +1429,7 @@ parse_sla(VALUE str, VALUE hash)
{
static const char pat_source[] =
#ifndef TIGHT_PARSER
"('?-?\\d+)/\\s*('?\\d+)(?:\\D\\s*('?-?\\d+))?"
"('?-?" NUMBER "+)/\\s*('?\\d+)(?:\\D\\s*('?-?\\d+))?"
#else
BOS
FPW_COM FPT_COM
Expand Down Expand Up @@ -1524,7 +1537,7 @@ parse_dot(VALUE str, VALUE hash)
{
static const char pat_source[] =
#ifndef TIGHT_PARSER
"('?-?\\d+)\\.\\s*('?\\d+)\\.\\s*('?-?\\d+)"
"('?-?" NUMBER "+)\\.\\s*('?\\d+)\\.\\s*('?-?\\d+)"
#else
BOS
FPW_COM FPT_COM
Expand Down Expand Up @@ -1684,7 +1697,7 @@ parse_mday(VALUE str, VALUE hash)
{
static const char pat_source[] =
#ifndef TIGHT_PARSER
"(\\d+)(st|nd|rd|th)\\b"
"(" NUMBER "+)(st|nd|rd|th)\\b"
#else
BOS
FPW_COM FPT_COM
Expand Down Expand Up @@ -1922,7 +1935,7 @@ parse_ddd(VALUE str, VALUE hash)
#ifdef TIGHT_PARSER
BOS
#endif
"([-+]?)(\\d{2,14})"
"([-+]?)(" NUMBER "{2,14})"
"(?:"
"\\s*"
"t?"
Expand Down
15 changes: 13 additions & 2 deletions test/date/test_date_parse.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
# frozen_string_literal: true
require 'test/unit'
require 'date'
require 'timeout'
require 'envutil'

class TestDateParse < Test::Unit::TestCase

Expand Down Expand Up @@ -585,6 +585,18 @@ def test__parse_odd_offset
assert_equal(5025, h[:offset])
end

def test__parse_too_long_year
str = "Jan 1" + "0" * 100_000
h = EnvUtil.timeout(1) {Date._parse(str, limit: 100_010)}
assert_equal(100_000, Math.log10(h[:year]))
assert_equal(1, h[:mon])

str = "Jan - 1" + "0" * 100_000
h = EnvUtil.timeout(1) {Date._parse(str, limit: 100_010)}
assert_equal(1, h[:mon])
assert_not_include(h, :year)
end

require 'time'

def test_parse__time
Expand Down Expand Up @@ -1297,6 +1309,5 @@ def test_length_limit
assert_raise(ArgumentError) { DateTime.jisx0301("1" * 1000) }

assert_raise(ArgumentError) { Date._parse("Jan " + "9" * 1000000) }
assert_raise(Timeout::Error) { Timeout.timeout(1) { Date._parse("Jan " + "9" * 1000000, limit: nil) } }
end
end