twitter-text - npm Package Compare versions

Comparing version 1.4.11 to 1.4.12

package.json

 {
   "name": "twitter-text"
   , "description": "official twitter text linkification"
-  , "version": "1.4.11"
+  , "version": "1.4.12"
   , "main": "./twitter-text.js"
@@ -6,0 +6,0 @@ , "homepage": "https://github.com/twitter/twitter-text-js"

test/twitter-text-conformance/README.md

@@ -43,2 +43,7 @@
 ## Changelog
+  * v1.4.8 - 2011-11-02 [ Git tag v1.4.8 ]
+    * [FIX] Extract URLs without protocol in CJK text
+    * [FIX] Do not extract URL in hashtag
+    * [FIX] Extract hashtag after bracket
+    * [FIX] Extract URL with '?' in fragment
 
@@ -45,0 +50,0 @@ * v1.4.7 - 2011-10-04 [ Git tag v1.4.7 ]

twitter-text.js

@@ -88,3 +88,3 @@ if (!window.twttr) {
     fromCode(0xFEFF), // BOM
-    fromCode(0xFFFF), // Special
+    fromCode(0xFFFF) // Special
   ];
@@ -98,6 +98,6 @@ addCharsToCharClass(INVALID_CHARS, 0x202A, 0x202E); // Directional change
   twttr.txt.regexen.atSigns = /[@＠]/;
-  twttr.txt.regexen.extractMentions = regexSupplant(/(^|[^a-zA-Z0-9_])(#{atSigns})([a-zA-Z0-9_]{1,20})(?=(.|$))/g);
+  twttr.txt.regexen.extractMentions = regexSupplant(/(^|[^a-zA-Z0-9_])(#{atSigns})([a-zA-Z0-9_]{1,20})/g);
   twttr.txt.regexen.extractReply = regexSupplant(/^(?:#{spaces})*#{atSigns}([a-zA-Z0-9_]{1,20})/);
   twttr.txt.regexen.listName = /[a-zA-Z][a-zA-Z0-9_\-\u0080-\u00ff]{0,24}/;
-  twttr.txt.regexen.extractMentionsOrLists = regexSupplant(/(^|[^a-zA-Z0-9_])(#{atSigns})([a-zA-Z0-9_]{1,20})(\/[a-zA-Z][a-zA-Z0-9_\-]{0,24})?(?=(.|$))/g);
+  twttr.txt.regexen.extractMentionsOrLists = regexSupplant(/(^|[^a-zA-Z0-9_])(#{atSigns})([a-zA-Z0-9_]{1,20})(\/[a-zA-Z][a-zA-Z0-9_\-]{0,24})?/g);
 
@@ -144,5 +144,6 @@ var nonLatinHashtagChars = [];
   // A hashtag must contain characters, numbers and underscores, but not all numbers.
-  twttr.txt.regexen.hashtagBoundary = regexSupplant(/(?:^|$|#{spaces}|[「」。、.,!！?？:;"'])/);
   twttr.txt.regexen.hashtagAlpha = regexSupplant(/[a-z_#{latinAccentChars}#{nonLatinHashtagChars}]/i);
   twttr.txt.regexen.hashtagAlphaNumeric = regexSupplant(/[a-z0-9_#{latinAccentChars}#{nonLatinHashtagChars}]/i);
+  twttr.txt.regexen.endHashtagMatch = /^(?:[#＃]|:\/\/)/;
+  twttr.txt.regexen.hashtagBoundary = regexSupplant(/(?:^|$|[^&\/a-z0-9_#{latinAccentChars}#{nonLatinHashtagChars}])/);
   twttr.txt.regexen.autoLinkHashtags = regexSupplant(/(#{hashtagBoundary})(#|＃)(#{hashtagAlphaNumeric}*#{hashtagAlpha}#{hashtagAlphaNumeric}*)/gi);
@@ -153,3 +154,3 @@ twttr.txt.regexen.autoLinkUsernamesOrLists = /(^|[^a-zA-Z0-9_]|RT:?)([@＠]+)([a-zA-Z0-9_]{1,20})(\/[a-zA-Z][a-zA-Z0-9_\-]{0,24})?/g;
   // URL related hash regex collection
-  twttr.txt.regexen.validPrecedingChars = regexSupplant(/(?:[^-\/"'!=A-Za-z0-9_@＠\.#{invalid_chars_group}]|^)/);
+  twttr.txt.regexen.validPrecedingChars = regexSupplant(/(?:[^-\/"'!=A-Za-z0-9_@＠#＃\.#{invalid_chars_group}]|^)/);
 
@@ -164,4 +165,4 @@ twttr.txt.regexen.invalidDomainChars = stringSupplant("#{punct}#{spaces_group}#{invalid_chars_group}", twttr.txt.regexen);
   twttr.txt.regexen.validDomain = regexSupplant(/(?:#{validSubdomain}*#{validDomainName}(?:#{validGTLD}|#{validCCTLD}|#{validPunycode}))/);
-  twttr.txt.regexen.validAsciiDomain = regexSupplant(/(?:(?:[a-z0-9#{latinAccentChars}]+)\.)+(?:#{validGTLD}|#{validCCTLD}|#{validPunycode})/i);
-  twttr.txt.regexen.validShortDomain = regexSupplant(/^#{validDomainName}#{validCCTLD}$/);
+  twttr.txt.regexen.validAsciiDomain = regexSupplant(/(?:(?:[a-z0-9#{latinAccentChars}]+)\.)+(?:#{validGTLD}|#{validCCTLD}|#{validPunycode})/gi);
+  twttr.txt.regexen.invalidShortDomain = regexSupplant(/^#{validDomainName}#{validCCTLD}$/);
 
@@ -187,3 +188,3 @@ twttr.txt.regexen.validPortNumber = regexSupplant(/[0-9]+/);
 
-  twttr.txt.regexen.validUrlQueryChars = /[a-z0-9!\*'\(\);:&=\+\$\/%#\[\]\-_\.,~|]/i;
+  twttr.txt.regexen.validUrlQueryChars = /[a-z0-9!?\*'\(\);:&=\+\$\/%#\[\]\-_\.,~|]/i;
   twttr.txt.regexen.validUrlQueryEndingChars = /[a-z0-9_&=#\/]/i;
@@ -400,3 +401,7 @@ twttr.txt.regexen.extractUrl = regexSupplant(
 
-    return text.replace(twttr.txt.regexen.autoLinkHashtags, function(match, before, hash, text) {
+    return text.replace(twttr.txt.regexen.autoLinkHashtags, function(match, before, hash, text, offset, chunk) {
+      var after = chunk.slice(offset + match.length);
+      if (after.match(twttr.txt.regexen.endHashtagMatch))
+        return match;
+
       var d = {
@@ -495,3 +500,4 @@ before: before,
 
-    text.replace(twttr.txt.regexen.extractMentions, function(match, before, atSign, screenName, after) {
+    text.replace(twttr.txt.regexen.extractMentions, function(match, before, atSign, screenName, offset, chunk) {
+      var after = chunk.slice(offset + match.length);
       if (!after.match(twttr.txt.regexen.endScreenNameMatch)) {
@@ -522,3 +528,4 @@ var startPosition = text.indexOf(atSign + screenName, position);
 
-    text.replace(twttr.txt.regexen.extractMentionsOrLists, function(match, before, atSign, screenName, slashListname, after) {
+    text.replace(twttr.txt.regexen.extractMentionsOrLists, function(match, before, atSign, screenName, slashListname, offset, chunk) {
+      var after = chunk.slice(offset + match.length);
       if (!after.match(twttr.txt.regexen.endScreenNameMatch)) {
@@ -546,3 +553,4 @@ slashListname = slashListname || '';
     var possibleScreenName = text.match(twttr.txt.regexen.extractReply);
-    if (!possibleScreenName) {
+    if (!possibleScreenName ||
+        RegExp.rightContext.match(twttr.txt.regexen.endScreenNameMatch)) {
       return null;
@@ -574,24 +582,41 @@ }
     text.replace(twttr.txt.regexen.extractUrl, function(match, all, before, url, protocol, domain, port, path, query) {
-      // If protocol is missing, check against validAsciiDomain
+      var startPosition = text.indexOf(url, position),
+          endPosition = startPosition + url.length;
+
+      // if protocol is missing and domain contains non-ASCII characters,
+      // extract ASCII-only domains.
       if (!protocol) {
-          ascii_domain = domain.match(twttr.txt.regexen.validAsciiDomain);
-          if (!ascii_domain) {
-            return;
+        var lastUrl,
+            lastUrlInvalidMatch = false,
+            asciiEndPosition = 0;
+        domain.replace(twttr.txt.regexen.validAsciiDomain, function(asciiDomain) {
+          var asciiStartPosition = domain.indexOf(asciiDomain, asciiEndPosition);
+          asciiEndPosition = asciiStartPosition + asciiDomain.length
+          lastUrl = {
+            url: asciiDomain,
+            indices: [startPosition + asciiStartPosition, startPosition + asciiEndPosition]
           }
-          url = url.replace(domain, ascii_domain[0]);
-          domain = ascii_domain[0];
-      }
-      // Regex in JavaScript doesn't support lookbehind, so we need to manually filter out
-      // the short URLs without protocol and slash, i.e., [domain].[ccTLD]
-      if (!protocol && !path && domain.match(twttr.txt.regexen.validShortDomain)) {
-        return;
-      }
+          lastUrlInvalidMatch = asciiDomain.match(twttr.txt.regexen.invalidShortDomain);
+          if (!lastUrlInvalidMatch) {
+            urls.push(lastUrl);
+          }
+        });
 
-      var startPosition = text.indexOf(url, position),
-          position = startPosition + url.length;
+        if (urls.length == 0) {
+          return;
+        }
 
-      urls.push({
-        url: url,
-        indices: [startPosition, position]
-      });
+        if (path) {
+          if (lastUrlInvalidMatch) {
+            urls.push(lastUrl);
+          }
+          lastUrl.url = url.replace(domain, lastUrl.url);
+          lastUrl.indices[1] = endPosition;
+        }
+      } else {
+        urls.push({
+          url: url,
+          indices: [startPosition, endPosition]
+        });
+      }
     });
@@ -621,3 +646,6 @@
 
-    text.replace(twttr.txt.regexen.autoLinkHashtags, function(match, before, hash, hashText) {
+    text.replace(twttr.txt.regexen.autoLinkHashtags, function(match, before, hash, hashText, offset, chunk) {
+      var after = chunk.slice(offset + match.length);
+      if (after.match(twttr.txt.regexen.endHashtagMatch))
+        return;
       var startPosition = text.indexOf(hash + hashText, position);
@@ -624,0 +652,0 @@ position = startPosition + hashText.length + 1;

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

New author

Supply chain risk

A new npm collaborator published a version of the package for the first time. New collaborators are usually benign additions to a project, but do indicate a change to the security surface area of a package.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Non-existent author

Supply chain risk

The package was published by an npm account that no longer exists.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

966654

increased by4.39%

Number of package files

43

increased by2.38%

Lines of code

20979

increased by3.95%

Number of high supply chain risk alerts

0

decreased by-100%

Worsened metrics

Number of medium supply chain risk alerts

1

increased byInfinity%

No dependency changes