Skip to content

Fix offsite URL performance with extra tests for policy change #726

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

Open
spassarop wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix offsite URL performance with extra tests for policy change #726

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
364 changes: 194 additions & 170 deletions src/main/resources/antisamy-anythinggoes.xml
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions src/main/resources/antisamy-ebay.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@
<regexp name="onsiteURL"
value="^(?!//)(?![\p{L}\p{N}\\\.\#@\$%\+&amp;;\-_~,\?=/!]*(&amp;colon))[\p{L}\p{N}\\\.\#@\$%\+&amp;;\-_~,\?=/!]*" />
<regexp name="offsiteURL"
value="(\s)*((ht|f)tp(s?)://|mailto:)[\p{L}\p{N}]+[\p{L}\p{N}\p{Zs}\.\#@\$%\+&amp;;:\-_~,\?=/!\(\)]*(\s)*" />
value="\s*+(?:(?:https?|ftps?)://|mailto:)[\p{L}\p{N}]++[\p{L}\p{N}\p{Zs}\.\#@\$%\+&amp;:,\-_~,\?=/!\(\)]*+\s*+" />

<regexp name="boolean" value="(true|false)" />
<regexp name="singlePrintable" value="[a-zA-Z0-9]{1}" /> <!-- \w allows the '_' character -->
Expand Down Expand Up @@ -77,7 +77,7 @@
<!-- This is for resources referenced from CSS (such as background images and other imported stylesheets) -->
<regexp name="cssOnsiteUri" value="url\(([\p{L}\p{N}\\/\.\?=\#&amp;;\-_~]+|\#(\w)+)\)" />
<regexp name="cssOffsiteUri"
value="url\((\s)*((ht|f)tp(s?)://)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;;:,\?=/\+!]*(\s)*\)" />
value="url\(\s*+(?:https?|ftps?)://[\p{L}\p{N}]++[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;:,\?=/\+!]*+\s*+\)" />

<!-- This if for CSS Identifiers -->
<regexp name="cssIdentifier" value="[a-zA-Z0-9\-_]+" />
Expand Down
4 changes: 2 additions & 2 deletions src/main/resources/antisamy-myspace.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@
<regexp name="onsiteURL"
value="^(?!//)(?![\p{L}\p{N}\\\.\#@\$%\+&amp;;\-_~,\?=/!]*(&amp;colon))[\p{L}\p{N}\\\.\#@\$%\+&amp;;\-_~,\?=/!]*" />
<regexp name="offsiteURL"
value="(\s)*((ht|f)tp(s?)://|mailto:)[\p{L}\p{N}]+[\p{L}\p{N}\p{Zs}\.\#@\$%\+&amp;;:\-_~,\?=/!\(\)]*(\s)*" />
value="\s*+(?:(?:https?|ftps?)://|mailto:)[\p{L}\p{N}]++[\p{L}\p{N}\p{Zs}\.\#@\$%\+&amp;:,\-_~,\?=/!\(\)]*+\s*+" />

<regexp name="boolean" value="(true|false)" />
<regexp name="singlePrintable" value="[a-zA-Z0-9]{1}" /> <!-- \w allows the '_' character -->
Expand Down Expand Up @@ -79,7 +79,7 @@
<!-- This is for resources referenced from CSS (such as background images and other imported stylesheets) -->
<regexp name="cssOnsiteUri" value="url\(([\p{L}\p{N}\\/\.\?=\#&amp;;\-_~]+|\#(\w)+)\)" />
<regexp name="cssOffsiteUri"
value="url\((\s)*((ht|f)tp(s?)://)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;;:,\?=/\+!]*(\s)*\)" />
value="url\(\s*+(?:https?|ftps?)://[\p{L}\p{N}]++[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;:,\?=/\+!]*+\s*+\)" />

<!-- This if for CSS Identifiers -->
<regexp name="cssIdentifier" value="[a-zA-Z0-9\-_]+" />
Expand Down
2 changes: 1 addition & 1 deletion src/main/resources/antisamy-slashdot.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
<regexp name="onsiteURL"
value="^(?!//)(?![\p{L}\p{N}\\\.\#@\$%\+&amp;;\-_~,\?=/!]*(&amp;colon))[\p{L}\p{N}\\\.\#@\$%\+&amp;;\-_~,\?=/!]*" />
<regexp name="offsiteURL"
value="(\s)*((ht|f)tp(s?)://|mailto:)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@\#\$%&amp;;:,\?=/\+!\(\)]*(\s)*" />
value="\s*+(?:(?:https?|ftps?)://|mailto:)[\p{L}\p{N}]++[\p{L}\p{N}\p{Zs}\.\#@\$%\+&amp;:,\-_~,\?=/!\(\)]*+\s*+" />

</common-regexps>

Expand Down
7 changes: 3 additions & 4 deletions src/main/resources/antisamy.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@
value="^(?!//)(?![\p{L}\p{N}\\\.\#@\$%\+&amp;;\-_~,\?=/!]*(&amp;colon))[\p{L}\p{N}\\\.\#@\$%\+&amp;;\-_~,\?=/!]*" />
<regexp name="anchoredURL" value="#(\w)+" />
<regexp name="offsiteURL"
value="(\s)*((ht|f)tp(s?)://|mailto:)[\p{L}\p{N}]+[\p{L}\p{N}\p{Zs}\.\#@\$%\+&amp;;:\-_~,\?=/!\(\)]*(\s)*" />
value="\s*+(?:(?:https?|ftps?)://|mailto:)[\p{L}\p{N}]++[\p{L}\p{N}\p{Zs}\.\#@\$%\+&amp;:,\-_~,\?=/!\(\)]*+\s*+" />

<regexp name="boolean" value="(true|false)" />
<regexp name="singlePrintable" value="[a-zA-Z0-9]{1}" /> <!-- \w allows the '_' character -->
Expand Down Expand Up @@ -83,7 +83,7 @@
<!-- This is for resources referenced from CSS (such as background images and other imported stylesheets) -->
<regexp name="cssOnsiteUri" value="url\(([\p{L}\p{N}\\/\.\?=\#&amp;;\-_~]+|\#(\w)+)\)" />
<regexp name="cssOffsiteUri"
value="url\((\s)*((ht|f)tp(s?)://)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;;:,\?=/\+!]*(\s)*\)" />
value="url\(\s*+(?:https?|ftps?)://[\p{L}\p{N}]++[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;:,\?=/\+!]*+\s*+\)" />

<!-- This if for CSS Identifiers -->
<regexp name="cssIdentifier" value="[a-zA-Z0-9\-_]+" />
Expand All @@ -110,8 +110,7 @@
value="rgb\(([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\)" />

<!-- Relative color values between 0%-100% are also allowed -->
<regexp name="rgbPercentage"
value="rgb\(([0-9][0-9]?|100)\.?\d*%,([0-9][0-9]?|100)\.?\d*%,([0-9][0-9]?|100)\.?\d*%\)" />
<regexp name="rgbPercentage" value="rgb\(([0-9][0-9]?|100)\.?\d*%,([0-9][0-9]?|100)\.?\d*%,([0-9][0-9]?|100)\.?\d*%\)" />

<!-- CSS2 Allowed System Color Values -->
<regexp name="systemColor"
Expand Down
Loading
Loading