aboutsummaryrefslogtreecommitdiff
path: root/lib/htmlparser
diff options
context:
space:
mode:
authorTulir Asokan <tulir@maunium.net>2018-04-14 18:09:02 +0300
committerGitHub <noreply@github.com>2018-04-14 18:09:02 +0300
commit53cdfb64c1773b63fb9432a1525b4ac4acb154fc (patch)
tree1c1aa180313abe8179d0b07591348e222b60483e /lib/htmlparser
parent14a84295d72a24a8bce8a71c240ab2b155ed5a1f (diff)
parentd060d10615434c557373ee00ba009cc8b583e881 (diff)
Merge pull request #18 from tulir/ui-refactor
Refactor UI to use interfaces and add advanced message rendering
Diffstat (limited to 'lib/htmlparser')
-rw-r--r--lib/htmlparser/doc.go3
-rw-r--r--lib/htmlparser/htmlparser.go142
2 files changed, 145 insertions, 0 deletions
diff --git a/lib/htmlparser/doc.go b/lib/htmlparser/doc.go
new file mode 100644
index 0000000..0e31960
--- /dev/null
+++ b/lib/htmlparser/doc.go
@@ -0,0 +1,3 @@
+// Package htmlparser contains a HTML parsing system similar to html.parser.HTMLParser in Python 3.
+// The parser uses x/net/html.Tokenizer in the background.
+package htmlparser
diff --git a/lib/htmlparser/htmlparser.go b/lib/htmlparser/htmlparser.go
new file mode 100644
index 0000000..5ef8d98
--- /dev/null
+++ b/lib/htmlparser/htmlparser.go
@@ -0,0 +1,142 @@
+// gomuks - A terminal Matrix client written in Go.
+// Copyright (C) 2018 Tulir Asokan
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package htmlparser
+
+import (
+ "io"
+ "strings"
+
+ "golang.org/x/net/html"
+)
+
+// HTMLProcessor contains the functions to process parsed HTML data.
+type HTMLProcessor interface {
+ // Preprocess is called before the parsing is started.
+ Preprocess()
+
+ // HandleStartTag is called with the tag name and attributes when
+ // the parser encounters a StartTagToken, except if the tag is
+ // always self-closing.
+ HandleStartTag(tagName string, attrs map[string]string)
+ // HandleSelfClosingTag is called with the tag name and attributes
+ // when the parser encounters a SelfClosingTagToken OR a StartTagToken
+ // with a tag that's always self-closing.
+ HandleSelfClosingTag(tagName string, attrs map[string]string)
+ // HandleText is called with the text when the parser encounters
+ // a TextToken.
+ HandleText(text string)
+ // HandleEndTag is called with the tag name when the parser encounters
+ // an EndTagToken.
+ HandleEndTag(tagName string)
+
+ // ReceiveError is called with the error when the parser encounters
+ // an ErrorToken that IS NOT io.EOF.
+ ReceiveError(err error)
+
+ // Postprocess is called after parsing is completed successfully.
+ // An unsuccessful parsing will trigger a ReceiveError() call.
+ Postprocess()
+}
+
+// HTMLParser wraps a net/html.Tokenizer and a HTMLProcessor to call
+// the HTMLProcessor with data from the Tokenizer.
+type HTMLParser struct {
+ *html.Tokenizer
+ processor HTMLProcessor
+}
+
+// NewHTMLParserFromTokenizer creates a new HTMLParser from an existing html Tokenizer.
+func NewHTMLParserFromTokenizer(z *html.Tokenizer, processor HTMLProcessor) HTMLParser {
+ return HTMLParser{
+ z,
+ processor,
+ }
+}
+
+// NewHTMLParserFromReader creates a Tokenizer with the given io.Reader and
+// then uses that to create a new HTMLParser.
+func NewHTMLParserFromReader(reader io.Reader, processor HTMLProcessor) HTMLParser {
+ return NewHTMLParserFromTokenizer(html.NewTokenizer(reader), processor)
+}
+
+// NewHTMLParserFromString creates a Tokenizer with a reader of the given
+// string and then uses that to create a new HTMLParser.
+func NewHTMLParserFromString(html string, processor HTMLProcessor) HTMLParser {
+ return NewHTMLParserFromReader(strings.NewReader(html), processor)
+}
+
+// SelfClosingTags is the list of tags that always call
+// HTMLProcessor.HandleSelfClosingTag() even if it is encountered
+// as a html.StartTagToken rather than html.SelfClosingTagToken.
+var SelfClosingTags = []string{"img", "br", "hr", "area", "base", "basefont", "input", "link", "meta"}
+
+func (parser HTMLParser) mapAttrs() map[string]string {
+ attrs := make(map[string]string)
+ hasMore := true
+ for hasMore {
+ var key, val []byte
+ key, val, hasMore = parser.TagAttr()
+ attrs[string(key)] = string(val)
+ }
+ return attrs
+}
+
+func (parser HTMLParser) isSelfClosing(tag string) bool {
+ for _, selfClosingTag := range SelfClosingTags {
+ if tag == selfClosingTag {
+ return true
+ }
+ }
+ return false
+}
+
+// Process parses the HTML using the tokenizer in this parser and
+// calls the appropriate functions of the HTML processor.
+func (parser HTMLParser) Process() {
+ parser.processor.Preprocess()
+Loop:
+ for {
+ tt := parser.Next()
+ switch tt {
+ case html.ErrorToken:
+ if parser.Err() != io.EOF {
+ parser.processor.ReceiveError(parser.Err())
+ return
+ }
+ break Loop
+ case html.TextToken:
+ parser.processor.HandleText(string(parser.Text()))
+ case html.StartTagToken, html.SelfClosingTagToken:
+ tagb, _ := parser.TagName()
+ attrs := parser.mapAttrs()
+ tag := string(tagb)
+
+ selfClosing := tt == html.SelfClosingTagToken || parser.isSelfClosing(tag)
+
+ if selfClosing {
+ parser.processor.HandleSelfClosingTag(tag, attrs)
+ } else {
+ parser.processor.HandleStartTag(tag, attrs)
+ }
+ case html.EndTagToken:
+ tagb, _ := parser.TagName()
+ parser.processor.HandleEndTag(string(tagb))
+ }
+ }
+
+ parser.processor.Postprocess()
+}