[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Emacs-diffs] master 8023715: Fix bugs found by 2019-09-29 regexp scanne
|
From: |
Paul Eggert |
|
Subject: |
[Emacs-diffs] master 8023715: Fix bugs found by 2019-09-29 regexp scanner |
|
Date: |
Fri, 4 Oct 2019 17:40:34 -0400 (EDT) |
branch: master
commit 8023715cf18d0b9e48fd0a4a72e4455edaa89813
Author: Paul Eggert <address@hidden>
Commit: Paul Eggert <address@hidden>
Fix bugs found by 2019-09-29 regexp scanner
Problems reported by Mattias Engdegård in:
https://lists.gnu.org/r/emacs-devel/2019-09/threads.html
* lisp/calendar/iso8601.el (iso8601--year-match)
(iso8601--full-date-match, iso8601--without-day-match)
(iso8601--week-date-match, iso8601--ordinal-date-match)
(iso8601--zone-match):
* lisp/textmodes/rst.el (rst-re-alist-def):
Put ‘-’ at the end of bracketed ranges, following the style
suggestion in the Elisp manual.
(iso8601--time-match): Use \([0-9]*\) instead of \([0-9]+\)?
to pacify the regexp scanner.
(iso8601-parse-time): Adjust accordingly.
* lisp/language/burmese.el (burmese-composable-pattern):
* lisp/language/indian.el (devanagari-composable-pattern)
(bengali-composable-pattern, gurmukhi-composable-pattern)
(gujarati-composable-pattern, oriya-composable-pattern)
(telugu-composable-pattern, kannada-composable-pattern)
(malayalam-composable-pattern):
Prefer [ab] to [a-b] when the characters differ by 1,
to pacify the regexp scanner.
* lisp/language/burmese.el (burmese-composable-pattern):
Fix missing-‘\u’ typos.
* lisp/language/indian.el (gurmukhi-composable-pattern):
Fix missing-‘\’ typo.
* lisp/language/tibetan.el (tibetan-regexp):
Quote ‘+’ in regexp to pacify the regexp scanner. Simplify.
* lisp/textmodes/rst.el (rst-re-alist-def): Fix ‘[]-'...]’
typo by putting the ‘-’ at end of the bracketed expression.
---
lisp/calendar/iso8601.el | 18 +++++++--------
lisp/language/burmese.el | 4 ++--
lisp/language/indian.el | 58 ++++++++++++++++++++++++------------------------
lisp/language/tibetan.el | 23 +++++++++----------
lisp/textmodes/rst.el | 8 +++----
5 files changed, 54 insertions(+), 57 deletions(-)
diff --git a/lisp/calendar/iso8601.el b/lisp/calendar/iso8601.el
index 3ff91d9..78a94d4 100644
--- a/lisp/calendar/iso8601.el
+++ b/lisp/calendar/iso8601.el
@@ -62,17 +62,17 @@
regexps "\\|"))
(defconst iso8601--year-match
- "\\([-+]\\)?\\([0-9][0-9][0-9][0-9]\\)")
+ "\\([+-]\\)?\\([0-9][0-9][0-9][0-9]\\)")
(defconst iso8601--full-date-match
- "\\([-+]\\)?\\([0-9][0-9][0-9][0-9]\\)-?\\([0-9][0-9]\\)-?\\([0-9][0-9]\\)")
+ "\\([+-]\\)?\\([0-9][0-9][0-9][0-9]\\)-?\\([0-9][0-9]\\)-?\\([0-9][0-9]\\)")
(defconst iso8601--without-day-match
- "\\([-+]\\)?\\([0-9][0-9][0-9][0-9]\\)-\\([0-9][0-9]\\)")
+ "\\([+-]\\)?\\([0-9][0-9][0-9][0-9]\\)-\\([0-9][0-9]\\)")
(defconst iso8601--outdated-date-match
"--\\([0-9][0-9]\\)-?\\([0-9][0-9]\\)")
(defconst iso8601--week-date-match
- "\\([-+]\\)?\\([0-9][0-9][0-9][0-9]\\)-?W\\([0-9][0-9]\\)-?\\([0-9]\\)?")
+ "\\([+-]\\)?\\([0-9][0-9][0-9][0-9]\\)-?W\\([0-9][0-9]\\)-?\\([0-9]\\)?")
(defconst iso8601--ordinal-date-match
- "\\([-+]\\)?\\([0-9][0-9][0-9][0-9]\\)-?\\([0-9][0-9][0-9]\\)")
+ "\\([+-]\\)?\\([0-9][0-9][0-9][0-9]\\)-?\\([0-9][0-9][0-9]\\)")
(defconst iso8601--date-match
(iso8601--concat-regexps
(list iso8601--year-match
@@ -83,10 +83,10 @@
iso8601--ordinal-date-match)))
(defconst iso8601--time-match
- "\\([0-9][0-9]\\):?\\([0-9][0-9]\\)?:?\\([0-9][0-9]\\)?[.,]?\\([0-9]+\\)?")
+ "\\([0-9][0-9]\\):?\\([0-9][0-9]\\)?:?\\([0-9][0-9]\\)?[.,]?\\([0-9]*\\)")
(defconst iso8601--zone-match
- "\\(Z\\|\\([-+]\\)\\([0-9][0-9]\\):?\\([0-9][0-9]\\)?\\)")
+ "\\(Z\\|\\([+-]\\)\\([0-9][0-9]\\):?\\([0-9][0-9]\\)?\\)")
(defconst iso8601--full-time-match
(concat "\\(" (replace-regexp-in-string "(" "(?:" iso8601--time-match) "\\)"
@@ -142,7 +142,7 @@ See `decode-time' for the meaning of FORM."
(defun iso8601-parse-date (string)
"Parse STRING (in ISO 8601 format) and return a `decode-time' value."
(cond
- ;; Just a year: [-+]YYYY.
+ ;; Just a year: [+-]YYYY.
((iso8601--match iso8601--year-match string)
(iso8601--decoded-time
:year (iso8601--adjust-year (match-string 1 string)
@@ -236,7 +236,7 @@ See `decode-time' for the meaning of FORM."
(string-to-number (match-string 2 time))))
(second (and (match-string 3 time)
(string-to-number (match-string 3 time))))
- (fraction (and (match-string 4 time)
+ (fraction (and (not (zerop (length (match-string 4 time))))
(string-to-number (match-string 4 time)))))
(when (and fraction
(eq form t))
diff --git a/lisp/language/burmese.el b/lisp/language/burmese.el
index 25425ec..7f2a99a 100644
--- a/lisp/language/burmese.el
+++ b/lisp/language/burmese.el
@@ -39,11 +39,11 @@
(defvar burmese-composable-pattern
(let ((table
'(("K" . "[\u1004\u105A]\u103A\u1039") ; KINZI sequence
- ("C" .
"[\u1000-\u102A\u103F\u1041-\u1049\u104E\u105A-\u105D\u1061\u1065-\u1066\u106E\u1071\u1075\u1081\u108E\uAA60-\uAA6F\uAA71-\uAA76]")
; consonant and vowel letter
+ ("C" .
"[\u1000-\u102A\u103F\u1041-\u1049\u104E\u105A-\u105D\u1061\u1065\u1066\u106E\u1071\u1075\u1081\u108E\uAA60-\uAA6F\uAA71-\uAA76]")
; consonant and vowel letter
("V" . "\u1039") ; VIRAMA
("A" . "\u103A") ; ASAT
("S" . "[\u1000-\u1019\u101C\u101E\u1020\u1021\u105A]") ; subscript
- ("M" . "[\u103B-\u103E\105E-\1060]") ; medial
+ ("M" . "[\u103B-\u103E\u105E-\u1060]") ; medial
("v" .
"[\u102B-\u103A\u103C-\u103E\u1062-\u1064\u1067-\u106D\u1071-\u1074\u1082-\u108D\u108F\u109A\u109C\uAA70]")))
; vowel sign, etc.
(regexp "\\(K\\)?C\\(VS\\)?\\(VS\\)?A?M*v*"))
(let ((case-fold-search nil))
diff --git a/lisp/language/indian.el b/lisp/language/indian.el
index f1e61a3..4013fac 100644
--- a/lisp/language/indian.el
+++ b/lisp/language/indian.el
@@ -139,14 +139,14 @@ South Indian language Malayalam is supported in this
language environment."))
(let ((table
'(("a" . "[\u0900-\u0902]") ; vowel modifier (above)
("A" . "\u0903") ; vowel modifier (post)
- ("V" . "[\u0904-\u0914\u0960-\u0961\u0972]") ; independent vowel
+ ("V" . "[\u0904-\u0914\u0960\u0961\u0972]") ; independent vowel
("C" . "[\u0915-\u0939\u0958-\u095F\u0979-\u097F]") ; consonant
("R" . "\u0930") ; RA
("n" . "\u093C") ; NUKTA
- ("v" . "[\u093E-\u094C\u094E\u0955\u0962-\u0963]") ; vowel sign
+ ("v" . "[\u093E-\u094C\u094E\u0955\u0962\u0963]") ; vowel sign
("H" . "\u094D") ; HALANT
- ("s" . "[\u0951-\u0952]") ; stress sign
- ("t" . "[\u0953-\u0954]") ; accent
+ ("s" . "[\u0951\u0952]") ; stress sign
+ ("t" . "[\u0953\u0954]") ; accent
("N" . "\u200C") ; ZWNJ
("J" . "\u200D") ; ZWJ
("X" . "[\u0900-\u097F]")))) ; all coverage
@@ -166,13 +166,13 @@ South Indian language Malayalam is supported in this
language environment."))
(defconst bengali-composable-pattern
(let ((table
'(("a" . "\u0981") ; SIGN CANDRABINDU
- ("A" . "[\u0982-\u0983]") ; SIGN ANUSVARA .. VISARGA
- ("V" . "[\u0985-\u0994\u09E0-\u09E1]") ; independent vowel
+ ("A" . "[\u0982\u0983]") ; SIGN ANUSVARA .. VISARGA
+ ("V" . "[\u0985-\u0994\u09E0\u09E1]") ; independent vowel
("C" . "[\u0995-\u09B9\u09DC-\u09DF\u09F1]") ; consonant
- ("B" . "[\u09AC\u09AF-\u09B0\u09F0]") ; BA, YA, RA
+ ("B" . "[\u09AC\u09AF\u09B0\u09F0]") ; BA, YA, RA
("R" . "[\u09B0\u09F0]") ; RA
("n" . "\u09BC") ; NUKTA
- ("v" . "[\u09BE-\u09CC\u09D7\u09E2-\u09E3]") ; vowel sign
+ ("v" . "[\u09BE-\u09CC\u09D7\u09E2\u09E3]") ; vowel sign
("H" . "\u09CD") ; HALANT
("T" . "\u09CE") ; KHANDA TA
("N" . "\u200C") ; ZWNJ
@@ -195,11 +195,11 @@ South Indian language Malayalam is supported in this
language environment."))
(defconst gurmukhi-composable-pattern
(let ((table
- '(("a" . "[\u0A01-\u0A02\u0A70]") ; SIGN ADAK BINDI .. BINDI, TIPPI
+ '(("a" . "[\u0A01\u0A02\u0A70]") ; SIGN ADAK BINDI .. BINDI, TIPPI
("A" . "\u0A03") ; SIGN VISARGA
("V" . "[\u0A05-\u0A14]") ; independent vowel
("C" . "[\u0A15-\u0A39\u0A59-\u0A5E]") ; consonant
- ("Y" . "[\u0A2F-u0A30\u0A35\u0A39]") ; YA, RA, VA, HA
+ ("Y" . "[\u0A2F-\u0A30\u0A35\u0A39]") ; YA, RA, VA, HA
("n" . "\u0A3C") ; NUKTA
("v" . "[\u0A3E-\u0A4C]") ; vowel sign
("H" . "\u0A4D") ; VIRAMA
@@ -221,13 +221,13 @@ South Indian language Malayalam is supported in this
language environment."))
(defconst gujarati-composable-pattern
(let ((table
- '(("a" . "[\u0A81-\u0A82]") ; SIGN CANDRABINDU .. ANUSVARA
+ '(("a" . "[\u0A81\u0A82]") ; SIGN CANDRABINDU .. ANUSVARA
("A" . "\u0A83") ; SIGN VISARGA
- ("V" . "[\u0A85-\u0A94\u0AE0-\u0AE1]") ; independent vowel
+ ("V" . "[\u0A85-\u0A94\u0AE0\u0AE1]") ; independent vowel
("C" . "[\u0A95-\u0AB9]") ; consonant
("R" . "\u0AB0") ; RA
("n" . "\u0ABC") ; NUKTA
- ("v" . "[\u0ABE-\u0ACC\u0AE2-\u0AE3]") ; vowel sign
+ ("v" . "[\u0ABE-\u0ACC\u0AE2\u0AE3]") ; vowel sign
("H" . "\u0ACD") ; VIRAMA
("N" . "\u200C") ; ZWNJ
("J" . "\u200D") ; ZWJ
@@ -248,13 +248,13 @@ South Indian language Malayalam is supported in this
language environment."))
(defconst oriya-composable-pattern
(let ((table
'(("a" . "\u0B01") ; SIGN CANDRABINDU
- ("A" . "[\u0B02-\u0B03]") ; SIGN ANUSVARA .. VISARGA
- ("V" . "[\u0B05-\u0B14\u0B60-\u0B61]") ; independent vowel
- ("C" . "[\u0B15-\u0B39\u0B5C-\u0B5D\u0B71]") ; consonant
- ("B" .
"[\u0B15-\u0B17\u0B1B-\u0B1D\u0B1F-\u0B21\u0B23-\u0B24\u0B27-\u0B30\u0B32-\u0B35\u0B38-\u0B39]")
; consonant with below form
+ ("A" . "[\u0B02\u0B03]") ; SIGN ANUSVARA .. VISARGA
+ ("V" . "[\u0B05-\u0B14\u0B60\u0B61]") ; independent vowel
+ ("C" . "[\u0B15-\u0B39\u0B5C\u0B5D\u0B71]") ; consonant
+ ("B" .
"[\u0B15-\u0B17\u0B1B-\u0B1D\u0B1F-\u0B21\u0B23\u0B24\u0B27-\u0B30\u0B32-\u0B35\u0B38\u0B39]")
; consonant with below form
("R" . "\u0B30") ; RA
("n" . "\u0B3C") ; NUKTA
- ("v" . "[\u0B3E-\u0B4C\u0B56-\u0B57\u0B62-\u0B63]") ; vowel sign
+ ("v" . "[\u0B3E-\u0B4C\u0B56\u0B57\u0B62\u0B63]") ; vowel sign
("H" . "\u0B4D") ; VIRAMA
("N" . "\u200C") ; ZWNJ
("J" . "\u200D") ; ZWJ
@@ -296,9 +296,9 @@ South Indian language Malayalam is supported in this
language environment."))
(defconst telugu-composable-pattern
(let ((table
'(("a" . "[\u0C01-\u0C03]") ; SIGN CANDRABINDU .. VISARGA
- ("V" . "[\u0C05-\u0C14\u0C60-\u0C61]") ; independent vowel
- ("C" . "[\u0C15-\u0C39\u0C58-\u0C59]") ; consonant
- ("v" . "[\u0C3E-\u0C4C\u0C55-\u0C56\u0C62-\u0C63]") ; vowel sign
+ ("V" . "[\u0C05-\u0C14\u0C60\u0C61]") ; independent vowel
+ ("C" . "[\u0C15-\u0C39\u0C58\u0C59]") ; consonant
+ ("v" . "[\u0C3E-\u0C4C\u0C55\u0C56\u0C62\u0C63]") ; vowel sign
("H" . "\u0C4D") ; VIRAMA
("N" . "\u200C") ; ZWNJ
("J" . "\u200D") ; ZWJ
@@ -318,12 +318,12 @@ South Indian language Malayalam is supported in this
language environment."))
(defconst kannada-composable-pattern
(let ((table
- '(("A" . "[\u0C82-\u0C83]") ; SIGN ANUSVARA .. VISARGA
- ("V" . "[\u0C85-\u0C94\u0CE0-\u0CE1]") ; independent vowel
- ("C" . "[\u0C95-\u0CB9\u0CDE]") ; consonant
+ '(("A" . "[\u0C82\u0C83]") ; SIGN ANUSVARA .. VISARGA
+ ("V" . "[\u0C85-\u0C94\u0CE0\u0CE1]") ; independent vowel
+ ("C" . "[\u0C95-\u0CB9\u0CDE]") ; consonant
("R" . "\u0CB0") ; RA
("n" . "\u0CBC") ; NUKTA
- ("v" . "[\u0CBE-\u0CCC\u0CD5-\u0CD6\u0CE2-\u0CE3]") ; vowel sign
+ ("v" . "[\u0CBE-\u0CCC\u0CD5\u0CD6\u0CE2\u0CE3]") ; vowel sign
("H" . "\u0CCD") ; VIRAMA
("N" . "\u200C") ; ZWNJ
("J" . "\u200D") ; ZWJ
@@ -343,11 +343,11 @@ South Indian language Malayalam is supported in this
language environment."))
(defconst malayalam-composable-pattern
(let ((table
- '(("A" . "[\u0D02-\u0D03]") ; SIGN ANUSVARA .. VISARGA
- ("V" . "[\u0D05-\u0D14\u0D60-\u0D61]") ; independent vowel
+ '(("A" . "[\u0D02\u0D03]") ; SIGN ANUSVARA .. VISARGA
+ ("V" . "[\u0D05-\u0D14\u0D60\u0D61]") ; independent vowel
("C" . "[\u0D15-\u0D39]") ; consonant
- ("Y" . "[\u0D2F-\u0D30\u0D32\u0D35]") ; YA, RA, LA, VA
- ("v" . "[\u0D3E-\u0D4C\u0D57\u0D62-\u0D63]") ; postbase matra
+ ("Y" . "[\u0D2F\u0D30\u0D32\u0D35]") ; YA, RA, LA, VA
+ ("v" . "[\u0D3E-\u0D4C\u0D57\u0D62\u0D63]") ; postbase matra
("H" . "\u0D4D") ; SIGN VIRAMA
("N" . "\u200C") ; ZWNJ
("J" . "\u200D") ; ZWJ
diff --git a/lisp/language/tibetan.el b/lisp/language/tibetan.el
index 4be25ce..b42a1e8 100644
--- a/lisp/language/tibetan.el
+++ b/lisp/language/tibetan.el
@@ -549,19 +549,16 @@
("སྨ" . "����")))
(defconst tibetan-regexp
- (let ((l (list tibetan-precomposed-transcription-alist
- tibetan-consonant-transcription-alist
- tibetan-vowel-transcription-alist
- tibetan-modifier-transcription-alist
- tibetan-subjoined-transcription-alist))
- (separator "\\|")
- tail pattern)
- (while l
- (setq tail (car l) l (cdr l))
- (while tail
- (setq pattern (cons separator (cons (car (car tail)) pattern))
- tail (cdr tail))))
- (apply 'concat (nreverse (cdr pattern))))
+ (let (pattern)
+ (dolist (alist (list tibetan-precomposed-transcription-alist
+ tibetan-consonant-transcription-alist
+ tibetan-vowel-transcription-alist
+ tibetan-modifier-transcription-alist
+ tibetan-subjoined-transcription-alist)
+ (apply #'concat (nreverse (cdr pattern))))
+ (dolist (key-val alist)
+ (setq pattern (cons "\\|" (cons (regexp-quote (car key-val))
+ pattern))))))
"Regexp matching a Tibetan transcription of a composable Tibetan sequence.
The result of matching is to be used for indexing alists at conversion
from a roman transcription to the corresponding Tibetan character.")
diff --git a/lisp/textmodes/rst.el b/lisp/textmodes/rst.el
index 88c44c0..b7438fb 100644
--- a/lisp/textmodes/rst.el
+++ b/lisp/textmodes/rst.el
@@ -388,8 +388,8 @@ in parentheses follows the development revision and the
time stamp.")
; item tag.
;; Inline markup (`ilm')
- (ilm-pfx (:alt "^" hws-prt "[-'\"([{<‘“«’/:]"))
- (ilm-sfx (:alt "$" hws-prt "[]-'\")}>’”»/:.,;!?\\]"))
+ (ilm-pfx (:alt "^" hws-prt "['\"([{<‘“«’/:-]"))
+ (ilm-sfx (:alt "$" hws-prt "[]'\")}>’”»/:.,;!?\\-]"))
;; Inline markup content (`ilc')
(ilcsgl-tag "\\S ") ; A single non-white character.
@@ -431,7 +431,7 @@ in parentheses follows the development revision and the
time stamp.")
(fld-tag ":" fldnam-tag ":") ; A field marker.
;; Options (`opt')
- (optsta-tag (:alt "[-+/]" "--")) ; Start of an option.
+ (optsta-tag (:alt "[+/-]" "--")) ; Start of an option.
(optnam-tag "\\sw" (:alt "-" "\\sw") "*") ; Name of an option.
(optarg-tag (:shy "[ =]\\S +")) ; Option argument.
(optsep-tag (:shy "," hws-prt)) ; Separator between options.
@@ -457,7 +457,7 @@ in parentheses follows the development revision and the
time stamp.")
; tag.
;; Symbol (`sym')
- (sym-prt "[-+.:_]") ; Non-word part of a symbol.
+ (sym-prt "[+.:_-]") ; Non-word part of a symbol.
(sym-tag (:shy "\\sw+" (:shy sym-prt "\\sw+") "*"))
;; URIs (`uri')
| [Prev in Thread] |
Current Thread |
[Next in Thread] |
- [Emacs-diffs] master 8023715: Fix bugs found by 2019-09-29 regexp scanner,
Paul Eggert <=