forked from gohugoio/hugo
-
Notifications
You must be signed in to change notification settings - Fork 6
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
parser/pageparser: File renames and splitting
See gohugoio#5324
- Loading branch information
Showing
4 changed files
with
197 additions
and
165 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,103 @@ | ||
| // Copyright 2018 The Hugo Authors. All rights reserved. | ||
| // | ||
| // Licensed under the Apache License, Version 2.0 (the "License"); | ||
| // you may not use this file except in compliance with the License. | ||
| // You may obtain a copy of the License at | ||
| // http://www.apache.org/licenses/LICENSE-2.0 | ||
| // | ||
| // Unless required by applicable law or agreed to in writing, software | ||
| // distributed under the License is distributed on an "AS IS" BASIS, | ||
| // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| // See the License for the specific language governing permissions and | ||
| // limitations under the License. | ||
|
|
||
| package pageparser | ||
|
|
||
| import "fmt" | ||
|
|
||
| type Item struct { | ||
| typ itemType | ||
| pos pos | ||
| Val string | ||
| } | ||
|
|
||
| func (i Item) IsText() bool { | ||
| return i.typ == tText | ||
| } | ||
|
|
||
| func (i Item) IsShortcodeName() bool { | ||
| return i.typ == tScName | ||
| } | ||
|
|
||
| func (i Item) IsLeftShortcodeDelim() bool { | ||
| return i.typ == tLeftDelimScWithMarkup || i.typ == tLeftDelimScNoMarkup | ||
| } | ||
|
|
||
| func (i Item) IsRightShortcodeDelim() bool { | ||
| return i.typ == tRightDelimScWithMarkup || i.typ == tRightDelimScNoMarkup | ||
| } | ||
|
|
||
| func (i Item) IsShortcodeClose() bool { | ||
| return i.typ == tScClose | ||
| } | ||
|
|
||
| func (i Item) IsShortcodeParam() bool { | ||
| return i.typ == tScParam | ||
| } | ||
|
|
||
| func (i Item) IsShortcodeParamVal() bool { | ||
| return i.typ == tScParamVal | ||
| } | ||
|
|
||
| func (i Item) IsShortcodeMarkupDelimiter() bool { | ||
| return i.typ == tLeftDelimScWithMarkup || i.typ == tRightDelimScWithMarkup | ||
| } | ||
|
|
||
| func (i Item) IsDone() bool { | ||
| return i.typ == tError || i.typ == tEOF | ||
| } | ||
|
|
||
| func (i Item) IsEOF() bool { | ||
| return i.typ == tEOF | ||
| } | ||
|
|
||
| func (i Item) IsError() bool { | ||
| return i.typ == tError | ||
| } | ||
|
|
||
| func (i Item) String() string { | ||
| switch { | ||
| case i.typ == tEOF: | ||
| return "EOF" | ||
| case i.typ == tError: | ||
| return i.Val | ||
| case i.typ > tKeywordMarker: | ||
| return fmt.Sprintf("<%s>", i.Val) | ||
| case len(i.Val) > 20: | ||
| return fmt.Sprintf("%.20q...", i.Val) | ||
| } | ||
| return fmt.Sprintf("[%s]", i.Val) | ||
| } | ||
|
|
||
| type itemType int | ||
|
|
||
| const ( | ||
| tError itemType = iota | ||
| tEOF | ||
|
|
||
| // shortcode items | ||
| tLeftDelimScNoMarkup | ||
| tRightDelimScNoMarkup | ||
| tLeftDelimScWithMarkup | ||
| tRightDelimScWithMarkup | ||
| tScClose | ||
| tScName | ||
| tScParam | ||
| tScParamVal | ||
|
|
||
| //itemIdentifier | ||
| tText // plain text, used for everything outside the shortcodes | ||
|
|
||
| // preserved for later - keywords come after this | ||
| tKeywordMarker | ||
| ) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,87 @@ | ||
| // Copyright 2018 The Hugo Authors. All rights reserved. | ||
| // | ||
| // Licensed under the Apache License, Version 2.0 (the "License"); | ||
| // you may not use this file except in compliance with the License. | ||
| // You may obtain a copy of the License at | ||
| // http://www.apache.org/licenses/LICENSE-2.0 | ||
| // | ||
| // Unless required by applicable law or agreed to in writing, software | ||
| // distributed under the License is distributed on an "AS IS" BASIS, | ||
| // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| // See the License for the specific language governing permissions and | ||
| // limitations under the License. | ||
|
|
||
| // Package pageparser provides a parser for Hugo content files (Markdown, HTML etc.) in Hugo. | ||
| // This implementation is highly inspired by the great talk given by Rob Pike called "Lexical Scanning in Go" | ||
| // It's on YouTube, Google it!. | ||
| // See slides here: http://cuddle.googlecode.com/hg/talk/lex.html | ||
| package pageparser | ||
|
|
||
| // The lexical scanning below | ||
|
|
||
| type Tokens struct { | ||
| lexer *pagelexer | ||
| token [3]Item // 3-item look-ahead is what we currently need | ||
| peekCount int | ||
| } | ||
|
|
||
| func (t *Tokens) Next() Item { | ||
| if t.peekCount > 0 { | ||
| t.peekCount-- | ||
| } else { | ||
| t.token[0] = t.lexer.nextItem() | ||
| } | ||
| return t.token[t.peekCount] | ||
| } | ||
|
|
||
| // backs up one token. | ||
| func (t *Tokens) Backup() { | ||
| t.peekCount++ | ||
| } | ||
|
|
||
| // backs up two tokens. | ||
| func (t *Tokens) Backup2(t1 Item) { | ||
| t.token[1] = t1 | ||
| t.peekCount = 2 | ||
| } | ||
|
|
||
| // backs up three tokens. | ||
| func (t *Tokens) Backup3(t2, t1 Item) { | ||
| t.token[1] = t1 | ||
| t.token[2] = t2 | ||
| t.peekCount = 3 | ||
| } | ||
|
|
||
| // check for non-error and non-EOF types coming next | ||
| func (t *Tokens) IsValueNext() bool { | ||
| i := t.Peek() | ||
| return i.typ != tError && i.typ != tEOF | ||
| } | ||
|
|
||
| // look at, but do not consume, the next item | ||
| // repeated, sequential calls will return the same item | ||
| func (t *Tokens) Peek() Item { | ||
| if t.peekCount > 0 { | ||
| return t.token[t.peekCount-1] | ||
| } | ||
| t.peekCount = 1 | ||
| t.token[0] = t.lexer.nextItem() | ||
| return t.token[0] | ||
| } | ||
|
|
||
| // Consume is a convencience method to consume the next n tokens, | ||
| // but back off Errors and EOF. | ||
| func (t *Tokens) Consume(cnt int) { | ||
| for i := 0; i < cnt; i++ { | ||
| token := t.Next() | ||
| if token.typ == tError || token.typ == tEOF { | ||
| t.Backup() | ||
| break | ||
| } | ||
| } | ||
| } | ||
|
|
||
| // LineNumber returns the current line number. Used for logging. | ||
| func (t *Tokens) LineNumber() int { | ||
| return t.lexer.lineNum() | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters