зеркало из https://github.com/mozilla/gecko-dev.git
Bug 1471884 [wpt PR 11707] - Consolidated fixes to character encoders/decoders, a=testonly
Automatic update from web-platform-testsConsolidated fixes to character encoders/decoders (#11707) * Fix EUC-JP reference decoder The relevant step fixed by this pull request says "Return error."; thus, the rest of the process should continue with the next iteration, rather than run the rest of the handler for the given byte. * Fix ISO-2022-JP reference implementation The relevant step in the Encoding Standard says "Prepend _lead_ and _byte_ to _stream_." However, the two bytes are prepended in the wrong order in the reference implementation. Note that under the Encoding Standard, "[w]hen one or more tokens are prepended to a stream, those tokens must be inserted, _in given order_, before the first token in the stream." (Note that the code, at the time of this request, moves _lead_ to the front of the array, then moves _byte_ to the front of the array.) There may be other issues like this elsewhere in the multiple-byte encoder reference implementations. * Fix bug in EUC-KR reference implementation Makes one "if" statement conditional rather than unconditional * Fix bug in Shift_JIS encoder * Fix bug in Big5 reference implementation * Fix Shift_JIS reference decoder To conform to the most recent Encoding Standard. -- wpt-commits: 0589266b84851660a1c70efb916f5d34fa5ebd7c wpt-pr: 11707
This commit is contained in:
Peter Occil
moz-wptsync-bot
Родитель
a37f593c10
Коммит
faee564332
|
|
@ -569073,7 +569073,7 @@
|
|||
"testharness"
|
||||
],
|
||||
"encoding/legacy-mb-japanese/euc-jp/eucjp-decoder.js": [
|
||||
"3bd6d8db793696c1827c31990e3e40e5181d9cac",
|
||||
"f0c9547639a3ab41a4b956c1d2afa2b1c0f27272",
|
||||
"support"
|
||||
],
|
||||
"encoding/legacy-mb-japanese/euc-jp/eucjp-encode-form-cseucpkdfmtjapanese.html": [
|
||||
|
|
@ -569213,7 +569213,7 @@
|
|||
"testharness"
|
||||
],
|
||||
"encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-decoder.js": [
|
||||
"3f9d6377755867c9b9b7d05ccaa88f459d0ca436",
|
||||
"09c51e38cafd3c0a7a506d8ffa3fa96700576fb3",
|
||||
"support"
|
||||
],
|
||||
"encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-form-csiso2022jp.html": [
|
||||
|
|
@ -569365,7 +569365,7 @@
|
|||
"testharness"
|
||||
],
|
||||
"encoding/legacy-mb-japanese/shift_jis/sjis-decoder.js": [
|
||||
"b62da9bead74bfa85fc74022aafbe5a56870e49d",
|
||||
"290e214851483bd34f3c876271b3d42f1613603a",
|
||||
"support"
|
||||
],
|
||||
"encoding/legacy-mb-japanese/shift_jis/sjis-encode-form-csshiftjis.html": [
|
||||
|
|
@ -569489,7 +569489,7 @@
|
|||
"support"
|
||||
],
|
||||
"encoding/legacy-mb-japanese/shift_jis/sjis-encoder.js": [
|
||||
"16f0b721a8c8a5609e31725359d8d44ea566fb69",
|
||||
"9383879790108e834d7e81c88a97ca86c2dad956",
|
||||
"support"
|
||||
],
|
||||
"encoding/legacy-mb-japanese/shift_jis/sjis_chars-csshiftjis.html": [
|
||||
|
|
@ -569609,7 +569609,7 @@
|
|||
"testharness"
|
||||
],
|
||||
"encoding/legacy-mb-korean/euc-kr/euckr-decoder.js": [
|
||||
"ee317acdc4c6ad8a737ac9f47a292015b0fab081",
|
||||
"ac458864fe09dac0f63cf18e86db0f3e5a88c2bf",
|
||||
"support"
|
||||
],
|
||||
"encoding/legacy-mb-korean/euc-kr/euckr-encode-form-cseuckr.html": [
|
||||
|
|
@ -569857,7 +569857,7 @@
|
|||
"testharness"
|
||||
],
|
||||
"encoding/legacy-mb-tchinese/big5/big5-decoder.js": [
|
||||
"895fb1caf07ea90bea9d34db70b0974f11d6c149",
|
||||
"dc90defd4da64abac6efbd1abf0aeadb9aef2b7b",
|
||||
"support"
|
||||
],
|
||||
"encoding/legacy-mb-tchinese/big5/big5-enc-ascii.html": [
|
||||
|
|
|
|||
|
|
@ -16,8 +16,9 @@ function eucjpDecoder(stream) {
|
|||
stream = stream.replace(/%/g, " ");
|
||||
stream = stream.replace(/[\s]+/g, " ").trim();
|
||||
var bytes = stream.split(" ");
|
||||
for (i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
for (var i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
var out = "";
|
||||
|
||||
var lead, byte, offset, ptr, cp;
|
||||
var jis0212flag = false;
|
||||
var eucjpLead = 0x00;
|
||||
|
|
@ -68,6 +69,7 @@ function eucjpDecoder(stream) {
|
|||
}
|
||||
if (byte >= 0x00 && byte <= 0x7f) bytes.unshift(byte);
|
||||
out += "<22>";
|
||||
continue;
|
||||
}
|
||||
if (byte >= 0x00 && byte <= 0x7f) {
|
||||
out += dec2char(byte);
|
||||
|
|
|
|||
|
|
@ -25,7 +25,7 @@ function iso2022jpDecoder(stream) {
|
|||
stream = stream.replace(/%/g, " ");
|
||||
stream = stream.replace(/[\s]+/g, " ").trim();
|
||||
var bytes = stream.split(" ");
|
||||
for (i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
for (var i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
var endofstream = 2000000;
|
||||
//bytes.push(endofstream)
|
||||
var out = "";
|
||||
|
|
@ -193,8 +193,8 @@ function iso2022jpDecoder(stream) {
|
|||
continue;
|
||||
}
|
||||
}
|
||||
bytes.unshift(lead);
|
||||
bytes.unshift(byte);
|
||||
// Prepend the sequence (lead, byte) to the stream
|
||||
bytes.unshift(lead, byte);
|
||||
outFlag = false;
|
||||
decState = outState;
|
||||
out += "<22>";
|
||||
|
|
|
|||
|
|
@ -16,7 +16,7 @@ function sjisDecoder(stream) {
|
|||
stream = stream.replace(/%/g, " ");
|
||||
stream = stream.replace(/[\s]+/g, " ").trim();
|
||||
var bytes = stream.split(" ");
|
||||
for (i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
for (var i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
var out = "";
|
||||
var lead, byte, leadoffset, offset, ptr, cp;
|
||||
var sjisLead = 0x00;
|
||||
|
|
@ -46,7 +46,7 @@ function sjisDecoder(stream) {
|
|||
else leadoffset = 0xc1;
|
||||
if ((byte >= 0x40 && byte <= 0x7e) || (byte >= 0x80 && byte <= 0xfc))
|
||||
ptr = (lead - leadoffset) * 188 + byte - offset;
|
||||
if (cp == null && ptr >= 8836 && ptr <= 10528) {
|
||||
if (ptr != null && ptr >= 8836 && ptr <= 10715) {
|
||||
out += dec2char(0xe000 + ptr - 8836);
|
||||
continue;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ function sjisEncoder(stream) {
|
|||
var cp;
|
||||
var finished = false;
|
||||
var endofstream = 2000000;
|
||||
|
||||
var temp, offset, leadoffset, first, second;
|
||||
while (!finished) {
|
||||
if (cps.length == 0) cp = endofstream;
|
||||
else cp = cps.shift();
|
||||
|
|
@ -73,7 +73,7 @@ function sjisEncoder(stream) {
|
|||
}
|
||||
if (cp >= 0xff61 && cp <= 0xff9f) {
|
||||
temp = cp - 0xff61 + 0xa1;
|
||||
out += temp.toString(16).toUpperCase();
|
||||
out += " " + temp.toString(16).toUpperCase();
|
||||
continue;
|
||||
}
|
||||
if (cp == 0x2212) {
|
||||
|
|
|
|||
|
|
@ -16,7 +16,7 @@ function euckrDecoder(stream) {
|
|||
stream = stream.replace(/%/g, " ");
|
||||
stream = stream.replace(/[\s]+/g, " ").trim();
|
||||
var bytes = stream.split(" ");
|
||||
for (i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
for (var i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
var out = "";
|
||||
var lead, byte, offset, ptr, cp;
|
||||
var euckrLead = 0x00;
|
||||
|
|
@ -41,7 +41,7 @@ function euckrDecoder(stream) {
|
|||
lead = euckrLead;
|
||||
ptr = null;
|
||||
euckrLead = 0x00;
|
||||
if (byte >= 0x41 || byte <= 0xfe)
|
||||
if (byte >= 0x41 && byte <= 0xfe)
|
||||
ptr = (lead - 0x81) * 190 + (byte - 0x41);
|
||||
if (ptr == null) cp = null;
|
||||
else cp = euckr[ptr];
|
||||
|
|
|
|||
|
|
@ -16,7 +16,7 @@ function big5Decoder(stream) {
|
|||
stream = stream.replace(/%/g, " ");
|
||||
stream = stream.replace(/[\s]+/g, " ").trim();
|
||||
var bytes = stream.split(" ");
|
||||
for (i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
for (var i = 0; i < bytes.length; i++) bytes[i] = parseInt(bytes[i], 16);
|
||||
var out = "";
|
||||
var lead, byte, offset, ptr, cp;
|
||||
var big5lead = 0x00;
|
||||
|
|
@ -47,24 +47,23 @@ function big5Decoder(stream) {
|
|||
ptr = (lead - 0x81) * 157 + (byte - offset);
|
||||
// "If there is a row in the table below whose first column is pointer, return the two code points listed in its second column"
|
||||
switch (ptr) {
|
||||
case "1133":
|
||||
case 1133:
|
||||
out += "Ê̄";
|
||||
continue;
|
||||
case "1135":
|
||||
case 1135:
|
||||
out += "Ê̌";
|
||||
continue;
|
||||
case "1164":
|
||||
case 1164:
|
||||
out += "ê̄";
|
||||
continue;
|
||||
case "1166":
|
||||
case 1166:
|
||||
out += "ê̌";
|
||||
continue;
|
||||
}
|
||||
if (ptr == null) cp = null;
|
||||
else cp = big5[ptr];
|
||||
if (cp == null && byte >= 0x00 && byte < 0x7f) {
|
||||
if (cp == null && byte >= 0x00 && byte <= 0x7f) {
|
||||
bytes.unshift(byte);
|
||||
continue;
|
||||
}
|
||||
if (cp == null) {
|
||||
out += "<22>";
|
||||
|
|
@ -73,7 +72,7 @@ function big5Decoder(stream) {
|
|||
out += dec2char(cp);
|
||||
continue;
|
||||
}
|
||||
if (byte >= 0x00 && byte < 0x7f) {
|
||||
if (byte >= 0x00 && byte <= 0x7f) {
|
||||
out += dec2char(byte);
|
||||
continue;
|
||||
}
|
||||
|
|
|
|||
Загрузка…
Ссылка в новой задаче