Documentation
¶
Index ¶
Constants ¶
View Source
const ( NoteTagPattern = `<<note[:=].+?>>` WildcardMatchingPattern = `<<match=\.\+>>` OptionalWildcardMatchingPattern = `<<match=\.\*>>` ReplaceableTextPattern = `<<(?:var;(?:name=(.+?);)?(?:original=(.*?);)?)?match=(.+?)>>` BeginOptionalLinePattern = `(m)^<<beginoptional(?:;name=.*?)?>>` BeginOptionalPattern = `<<beginoptional(?:;name=.*?)?>>` OmitableLine = "<<omitable>>\n" Omitable = "<<omitable>>" EndOptionalPattern = `<<endoptional>>` ReplaceEndPattern = `<</omitable>>` CommentBlockOutsidePattern = `(?m)^\s*(?:/\*|-{2,3}\[=*\[)|(?:\*/|]=*])\s*$` CommentBlockInsidePattern = `(?m)^\s*[*#]{1,6}|\*{1,6}$` CommentLinePattern = `(?m)^\s*(?://|>|--|;{1,4})` HtmlStyleCommentPattern = `(?m)^\s*<!--|-->\s*$` DashLikePattern = "[\u002D\u2010\u2011\u2013\u2014\u2015\u2212\uFE58\uFE63\uFE0D]" QuoteLikePattern = "[\u0022\u0027\u0060\u00B4\u2018\u2019\u201C\u201D]+" HTTPPattern = `(?i)https?` BulletsPattern = "(?m)^\\s*[*+\u2022-]\\s+" NumberingPattern = "(?m)(?:\\s|^)\\(?(?:\\w|[\\divx#]+)[.)][\\s$]" SplitWords = `(?m)\b-$\s+\b` HorizontalRulePattern = `(?m)^\s*[*=-]{3,}` Copyright = `©|\([cC]\)` ControlCharacters = "[\u0000-\u0007\u000E-\u001B]" OddCharactersPattern = "(?im)^\\^l$|\u0080|\u0099|\u009C|\u009D|\u00AC|\u00E2|\u00A7|\u00C2|\u00A4|\u0153|\u20AC|\uFFFD" LeadingWhitespacePattern = `^\s` MiddleWhitespacePattern = "(?:\\s|\u00A0|\u2028|\u00B7)+" TrailingWhitespacePattern = `\s$` )
Variables ¶
View Source
var ( Logger = log.NewLogger(log.INFO) NoteTagPatternRE = regexp.MustCompile(NoteTagPattern) WildcardMatchingPatternRE = regexp.MustCompile(WildcardMatchingPattern) OptionalWildcardMatchingPatternRE = regexp.MustCompile(OptionalWildcardMatchingPattern) BeginOptionalLinePatternRE = regexp.MustCompile(BeginOptionalLinePattern) BeginOptionalPatternRE = regexp.MustCompile(BeginOptionalPattern) EndOptionalPatternRE = regexp.MustCompile(EndOptionalPattern) HorizontalRulePatternRE = regexp.MustCompile(HorizontalRulePattern) SplitWordsRE = regexp.MustCompile(SplitWords) HTTPPatternRE = regexp.MustCompile(HTTPPattern) QuoteLikeRE = regexp.MustCompile(QuoteLikePattern) DashLikeRE = regexp.MustCompile(DashLikePattern) ReplaceableTextPatternRE = regexp.MustCompile(ReplaceableTextPattern) BulletsPatternRE = regexp.MustCompile(BulletsPattern) NumberingPatternRE = regexp.MustCompile(NumberingPattern) CommentBlockOutsideRE = regexp.MustCompile(CommentBlockOutsidePattern) CommentBlockInsideRE = regexp.MustCompile(CommentBlockInsidePattern) HtmlStyleCommentRE = regexp.MustCompile(HtmlStyleCommentPattern) CommentLineRE = regexp.MustCompile(CommentLinePattern) MiddleWhitespaceRE = regexp.MustCompile(MiddleWhitespacePattern) LeadingWhitespaceRE = regexp.MustCompile(LeadingWhitespacePattern) TrailingWhitespaceRE = regexp.MustCompile(TrailingWhitespacePattern) OddCharactersPatternRE = regexp.MustCompile(OddCharactersPattern) CopyrightRE = regexp.MustCompile(Copyright) ControlCharactersRE = regexp.MustCompile(ControlCharacters) )
Functions ¶
This section is empty.
Types ¶
type CaptureGroup ¶
type NormalizationData ¶
type NormalizationData struct { // original input text OriginalText string // normalized version of the input text NormalizedText string IndexMap []int CaptureGroups []*CaptureGroup Hash Digest IsTemplate bool // contains filtered or unexported fields }
NormalizationData holds the input data and its normalized text
func NewNormalizationData ¶
func NewNormalizationData(originalText string, isTemplate bool) *NormalizationData
func (*NormalizationData) NormalizeText ¶
func (n *NormalizationData) NormalizeText() error
NormalizeText normalizes the input text
Click to show internal directories.
Click to hide internal directories.