Package com.google.googlejavaformat.java.javadoc

Class JavadocLexer

java.lang.Object

com.google.googlejavaformat.java.javadoc.JavadocLexer

final class JavadocLexer
extends java.lang.Object

Lexer for the Javadoc formatter.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
(package private) static class	JavadocLexer.LexException

Field Summary

Fields

Modifier and Type	Field	Description
private static java.util.regex.Pattern	BLOCKQUOTE_CLOSE_PATTERN
private static java.util.regex.Pattern	BLOCKQUOTE_OPEN_PATTERN
private static java.util.regex.Pattern	BR_PATTERN
private NestingCounter	braceDepth
private static java.util.regex.Pattern	CODE_CLOSE_PATTERN
private static java.util.regex.Pattern	CODE_OPEN_PATTERN
private NestingCounter	codeDepth
private static java.util.regex.Pattern	FOOTER_TAG_PATTERN
private static java.util.regex.Pattern	HEADER_CLOSE_PATTERN
private static java.util.regex.Pattern	HEADER_OPEN_PATTERN
private static java.util.regex.Pattern	HTML_COMMENT_PATTERN
private static java.util.regex.Pattern	INLINE_TAG_OPEN_PATTERN
private CharStream	input
private static java.util.regex.Pattern	LIST_CLOSE_PATTERN
private static java.util.regex.Pattern	LIST_ITEM_CLOSE_PATTERN
private static java.util.regex.Pattern	LIST_ITEM_OPEN_PATTERN
private static java.util.regex.Pattern	LIST_OPEN_PATTERN
private static java.util.regex.Pattern	LITERAL_PATTERN
private static java.util.regex.Pattern	MOE_BEGIN_STRIP_COMMENT_PATTERN
private static java.util.regex.Pattern	MOE_END_STRIP_COMMENT_PATTERN
private static com.google.common.base.CharMatcher	NEWLINE
private static java.util.regex.Pattern	NEWLINE_PATTERN
private static java.util.regex.Pattern	NON_UNIX_LINE_ENDING
private static java.util.regex.Pattern	PARAGRAPH_CLOSE_PATTERN
private static java.util.regex.Pattern	PARAGRAPH_OPEN_PATTERN
private static java.util.regex.Pattern	PRE_CLOSE_PATTERN
private static java.util.regex.Pattern	PRE_OPEN_PATTERN
private NestingCounter	preDepth
private boolean	somethingSinceNewline
private static java.util.regex.Pattern	TABLE_CLOSE_PATTERN
private static java.util.regex.Pattern	TABLE_OPEN_PATTERN
private NestingCounter	tableDepth

Constructor Summary

Constructors

Modifier	Constructor	Description
private	JavadocLexer(CharStream input)

Method Summary

Modifier and Type	Method	Description
private void	checkMatchingTags()
private static java.util.regex.Pattern	closeTagPattern(java.lang.String namePattern)
private Token.Type	consumeToken()
private static void	deindentPreCodeBlock(com.google.common.collect.ImmutableList.Builder<Token> output, com.google.common.collect.PeekingIterator<Token> tokens)
private static com.google.common.collect.ImmutableList<Token>	deindentPreCodeBlocks(java.util.List<Token> input)	Adjust indentation inside `
private static java.util.regex.Pattern	fullCommentPattern()
private com.google.common.collect.ImmutableList<Token>	generateTokens()
private static boolean	hasMultipleNewlines(java.lang.String s)
private static com.google.common.collect.ImmutableList<Token>	inferParagraphTags(java.util.List<Token> input)	Where the input has two consecutive line breaks between literals, insert a <p> tag between the literals.
private static com.google.common.collect.ImmutableList<Token>	joinAdjacentLiteralsAndAdjacentWhitespace(java.util.List<Token> input)	Join together adjacent literal tokens, and join together adjacent whitespace tokens.
(package private) static com.google.common.collect.ImmutableList<Token>	lex(java.lang.String input)	Takes a Javadoc comment, including ∕✱✱ and ✱∕, and returns tokens, including ∕✱✱ and ✱∕.
private static java.lang.String	normalizeLineEndings(java.lang.String input)	The lexer crashes on windows line endings, so for now just normalize to `\n`.
private static java.util.regex.Pattern	openTagPattern(java.lang.String namePattern)
private static com.google.common.collect.ImmutableList<Token>	optionalizeSpacesAfterLinks(java.util.List<Token> input)	Replaces whitespace after a href=...> token with an "optional link break." This allows us to output either <a href=foo>foo</a> or <a href=foo>\nfoo</a>, depending on how much space we have left on the line.
private boolean	preserveExistingFormatting()
private Token	readToken()
private static java.lang.String	stripJavadocBeginAndEnd(java.lang.String input)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

NON_UNIX_LINE_ENDING

private static final java.util.regex.Pattern NON_UNIX_LINE_ENDING

input

private final CharStream input

braceDepth

private final NestingCounter braceDepth

preDepth

private final NestingCounter preDepth

codeDepth

private final NestingCounter codeDepth

tableDepth

private final NestingCounter tableDepth

somethingSinceNewline

private boolean somethingSinceNewline

NEWLINE

private static final com.google.common.base.CharMatcher NEWLINE

NEWLINE_PATTERN

private static final java.util.regex.Pattern NEWLINE_PATTERN

FOOTER_TAG_PATTERN

private static final java.util.regex.Pattern FOOTER_TAG_PATTERN

MOE_BEGIN_STRIP_COMMENT_PATTERN

private static final java.util.regex.Pattern MOE_BEGIN_STRIP_COMMENT_PATTERN

MOE_END_STRIP_COMMENT_PATTERN

private static final java.util.regex.Pattern MOE_END_STRIP_COMMENT_PATTERN

HTML_COMMENT_PATTERN

private static final java.util.regex.Pattern HTML_COMMENT_PATTERN

PRE_OPEN_PATTERN

private static final java.util.regex.Pattern PRE_OPEN_PATTERN

PRE_CLOSE_PATTERN

private static final java.util.regex.Pattern PRE_CLOSE_PATTERN

CODE_OPEN_PATTERN

private static final java.util.regex.Pattern CODE_OPEN_PATTERN

CODE_CLOSE_PATTERN

private static final java.util.regex.Pattern CODE_CLOSE_PATTERN

TABLE_OPEN_PATTERN

private static final java.util.regex.Pattern TABLE_OPEN_PATTERN

TABLE_CLOSE_PATTERN

private static final java.util.regex.Pattern TABLE_CLOSE_PATTERN

LIST_OPEN_PATTERN

private static final java.util.regex.Pattern LIST_OPEN_PATTERN

LIST_CLOSE_PATTERN

private static final java.util.regex.Pattern LIST_CLOSE_PATTERN

LIST_ITEM_OPEN_PATTERN

private static final java.util.regex.Pattern LIST_ITEM_OPEN_PATTERN

LIST_ITEM_CLOSE_PATTERN

private static final java.util.regex.Pattern LIST_ITEM_CLOSE_PATTERN

HEADER_OPEN_PATTERN

private static final java.util.regex.Pattern HEADER_OPEN_PATTERN

HEADER_CLOSE_PATTERN

private static final java.util.regex.Pattern HEADER_CLOSE_PATTERN

PARAGRAPH_OPEN_PATTERN

private static final java.util.regex.Pattern PARAGRAPH_OPEN_PATTERN

PARAGRAPH_CLOSE_PATTERN

private static final java.util.regex.Pattern PARAGRAPH_CLOSE_PATTERN

BLOCKQUOTE_OPEN_PATTERN

private static final java.util.regex.Pattern BLOCKQUOTE_OPEN_PATTERN

BLOCKQUOTE_CLOSE_PATTERN

private static final java.util.regex.Pattern BLOCKQUOTE_CLOSE_PATTERN

BR_PATTERN

private static final java.util.regex.Pattern BR_PATTERN

INLINE_TAG_OPEN_PATTERN

private static final java.util.regex.Pattern INLINE_TAG_OPEN_PATTERN

LITERAL_PATTERN

private static final java.util.regex.Pattern LITERAL_PATTERN

Constructor Detail

JavadocLexer

private JavadocLexer(CharStream input)

Method Detail

lex

static com.google.common.collect.ImmutableList<Token> lex(java.lang.String input)
                                                   throws JavadocLexer.LexException

Takes a Javadoc comment, including ∕✱✱ and ✱∕, and returns tokens, including ∕✱✱ and ✱∕.

Throws:

JavadocLexer.LexException

normalizeLineEndings

private static java.lang.String normalizeLineEndings(java.lang.String input)

The lexer crashes on windows line endings, so for now just normalize to `\n`.

stripJavadocBeginAndEnd

private static java.lang.String stripJavadocBeginAndEnd(java.lang.String input)

generateTokens

private com.google.common.collect.ImmutableList<Token> generateTokens()
                                                               throws JavadocLexer.LexException

Throws:

JavadocLexer.LexException

readToken

private Token readToken()
                 throws JavadocLexer.LexException

Throws:

JavadocLexer.LexException

consumeToken

private Token.Type consumeToken()
                         throws JavadocLexer.LexException

Throws:

JavadocLexer.LexException

preserveExistingFormatting

private boolean preserveExistingFormatting()

checkMatchingTags

private void checkMatchingTags()
                        throws JavadocLexer.LexException

Throws:

JavadocLexer.LexException

joinAdjacentLiteralsAndAdjacentWhitespace

private static com.google.common.collect.ImmutableList<Token> joinAdjacentLiteralsAndAdjacentWhitespace(java.util.List<Token> input)

Join together adjacent literal tokens, and join together adjacent whitespace tokens.

For literal tokens, this means something like ["<b>", "foo", "</b>"] => ["<b>foo</b>"]. See LITERAL_PATTERN for discussion of why those tokens are separate to begin with.

Whitespace tokens are treated analogously. We don't really "want" to join whitespace tokens, but in the course of joining literals, we incidentally join whitespace, too. We do take advantage of the joining later on: It simplifies inferParagraphTags(java.util.List<com.google.googlejavaformat.java.javadoc.Token>).

Note that we do not merge a literal token and a whitespace token together.

inferParagraphTags

private static com.google.common.collect.ImmutableList<Token> inferParagraphTags(java.util.List<Token> input)

Where the input has two consecutive line breaks between literals, insert a <p> tag between the literals.

This method must be called after joinAdjacentLiteralsAndAdjacentWhitespace(java.util.List<com.google.googlejavaformat.java.javadoc.Token>), as it assumes that adjacent whitespace tokens have already been joined.

optionalizeSpacesAfterLinks

private static com.google.common.collect.ImmutableList<Token> optionalizeSpacesAfterLinks(java.util.List<Token> input)

Replaces whitespace after a href=...> token with an "optional link break." This allows us to output either <a href=foo>foo</a> or <a href=foo>\nfoo</a>, depending on how much space we have left on the line.

This method must be called after joinAdjacentLiteralsAndAdjacentWhitespace(java.util.List<com.google.googlejavaformat.java.javadoc.Token>), as it assumes that adjacent whitespace tokens have already been joined.

deindentPreCodeBlocks

private static com.google.common.collect.ImmutableList<Token> deindentPreCodeBlocks(java.util.List<Token> input)

Adjust indentation inside `

` blocks.

 <p>Also trim leading and trailing blank lines, and move the trailing `` to its own line.

deindentPreCodeBlock

private static void deindentPreCodeBlock(com.google.common.collect.ImmutableList.Builder<Token> output,
                                         com.google.common.collect.PeekingIterator<Token> tokens)

hasMultipleNewlines

private static boolean hasMultipleNewlines(java.lang.String s)

fullCommentPattern

private static java.util.regex.Pattern fullCommentPattern()

openTagPattern

private static java.util.regex.Pattern openTagPattern(java.lang.String namePattern)

closeTagPattern

private static java.util.regex.Pattern closeTagPattern(java.lang.String namePattern)