Skip to content

Remove the requirement for CharStream patterns to be anchored with ^. #1348

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
copybara-service merged 1 commit into from
Mar 16, 2026
Merged

Remove the requirement for CharStream patterns to be anchored with ^. #1348

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
4 changes: 1 addition & 3 deletions core/src/main/java/com/google/googlejavaformat/java/javadoc/CharStream.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@

package com.google.googlejavaformat.java.javadoc;

import static com.google.common.base.Preconditions.checkArgument;
import static com.google.common.base.Preconditions.checkNotNull;

import java.util.regex.Matcher;
Expand Down Expand Up @@ -50,10 +49,9 @@ boolean tryConsume(String expected) {
*/
boolean tryConsumeRegex(Pattern pattern) {
Matcher matcher = pattern.matcher(input).region(start, input.length());
if (!matcher.find()) {
if (!matcher.lookingAt()) {
return false;
}
checkArgument(matcher.start() == start);
tokenEnd = matcher.end();
return true;
}
Expand Down
26 changes: 11 additions & 15 deletions core/src/main/java/com/google/googlejavaformat/java/javadoc/JavadocLexer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -393,7 +393,7 @@ private static ImmutableList<Token> optionalizeSpacesAfterLinks(List<Token> inpu
ImmutableList.Builder<Token> output = ImmutableList.builder();

for (PeekingIterator<Token> tokens = peekingIterator(input.iterator()); tokens.hasNext(); ) {
if (tokens.peek().getType() == LITERAL && tokens.peek().getValue().matches("^href=[^>]*>")) {
if (tokens.peek().getType() == LITERAL && tokens.peek().getValue().matches("href=[^>]*>")) {
output.add(tokens.next());

if (tokens.peek().getType() == WHITESPACE) {
Expand Down Expand Up @@ -519,18 +519,18 @@ private static boolean hasMultipleNewlines(String s) {
* We'd remove the trailing whitespace later on (in JavaCommentsHelper.rewrite), but I feel safer
* stripping it now: It otherwise might confuse our line-length count, which we use for wrapping.
*/
private static final Pattern NEWLINE_PATTERN = compile("^[ \t]*\n[ \t]*[*]?[ \t]?");
private static final Pattern NEWLINE_PATTERN = compile("[ \t]*\n[ \t]*[*]?[ \t]?");

// We ensure elsewhere that we match this only at the beginning of a line.
// Only match tags that start with a lowercase letter, to avoid false matches on unescaped
// annotations inside code blocks.
// Match "@param <T>" specially in case the <T> is a <P> or other HTML tag we treat specially.
private static final Pattern FOOTER_TAG_PATTERN = compile("^@(param\\s+<\\w+>|[a-z]\\w*)");
private static final Pattern FOOTER_TAG_PATTERN = compile("@(param\\s+<\\w+>|[a-z]\\w*)");
private static final Pattern MOE_BEGIN_STRIP_COMMENT_PATTERN =
compile("^<!--\\s*M" + "OE:begin_intracomment_strip\\s*-->");
compile("<!--\\s*M" + "OE:begin_intracomment_strip\\s*-->");
private static final Pattern MOE_END_STRIP_COMMENT_PATTERN =
compile("^<!--\\s*M" + "OE:end_intracomment_strip\\s*-->");
private static final Pattern HTML_COMMENT_PATTERN = fullCommentPattern();
compile("<!--\\s*M" + "OE:end_intracomment_strip\\s*-->");
private static final Pattern HTML_COMMENT_PATTERN = compile("<!--.*?-->", DOTALL);
private static final Pattern PRE_OPEN_PATTERN = openTagPattern("pre");
private static final Pattern PRE_CLOSE_PATTERN = closeTagPattern("pre");
private static final Pattern CODE_OPEN_PATTERN = openTagPattern("code");
Expand All @@ -548,8 +548,8 @@ private static boolean hasMultipleNewlines(String s) {
private static final Pattern BLOCKQUOTE_OPEN_PATTERN = openTagPattern("blockquote");
private static final Pattern BLOCKQUOTE_CLOSE_PATTERN = closeTagPattern("blockquote");
private static final Pattern BR_PATTERN = openTagPattern("br");
private static final Pattern SNIPPET_TAG_OPEN_PATTERN = compile("^[{]@snippet\\b");
private static final Pattern INLINE_TAG_OPEN_PATTERN = compile("^[{]@\\w*");
private static final Pattern SNIPPET_TAG_OPEN_PATTERN = compile("[{]@snippet\\b");
private static final Pattern INLINE_TAG_OPEN_PATTERN = compile("[{]@\\w*");
/*
* We exclude < so that we don't swallow following HTML tags. This lets us fix up "foo<p>" (~400
* hits in Google-internal code). We will join unnecessarily split "words" (like "foo<b>bar</b>")
Expand All @@ -560,18 +560,14 @@ private static boolean hasMultipleNewlines(String s) {
* with matching only one character here. That would eliminate the need for the regex entirely.
* That might be faster or slower than what we do now.
*/
private static final Pattern LITERAL_PATTERN = compile("^.[^ \t\n@<{}*]*", DOTALL);

private static Pattern fullCommentPattern() {
return compile("^<!--.*?-->", DOTALL);
}
private static final Pattern LITERAL_PATTERN = compile(".[^ \t\n@<{}*]*", DOTALL);

private static Pattern openTagPattern(String namePattern) {
return compile(format("^<(?:%s)\\b[^>]*>", namePattern), CASE_INSENSITIVE);
return compile(format("<(?:%s)\\b[^>]*>", namePattern), CASE_INSENSITIVE);
}

private static Pattern closeTagPattern(String namePattern) {
return compile(format("^</(?:%s)\\b[^>]*>", namePattern), CASE_INSENSITIVE);
return compile(format("</(?:%s)\\b[^>]*>", namePattern), CASE_INSENSITIVE);
}

static class LexException extends Exception {}
Expand Down
Loading