From 77b0ad1e806580e47e4f682dfb912c55e1411b73 Mon Sep 17 00:00:00 2001 From: Andrew Balholm Date: Thu, 24 Nov 2011 09:28:58 +1100 Subject: [PATCH] html: parse DOCTYPE into name and public and system identifiers Pass tests2.dat, test 59: >--> | | | | | ">" | | "-->" Pass all the tests in doctype01.dat. Also pass tests2.dat, test 60:

R=nigeltao CC=golang-dev https://golang.org/cl/5437045 --- src/pkg/html/parse.go | 58 +++++++++++++++++++++++++++++++++++--- src/pkg/html/parse_test.go | 21 ++++++++++++-- src/pkg/html/render.go | 56 ++++++++++++++++++++++++++++++++++++ 3 files changed, 129 insertions(+), 6 deletions(-) diff --git a/src/pkg/html/parse.go b/src/pkg/html/parse.go index 36204895b9..041c5390ed 100644 --- a/src/pkg/html/parse.go +++ b/src/pkg/html/parse.go @@ -321,6 +321,59 @@ func (p *parser) resetInsertionMode() { const whitespace = " \t\r\n\f" +// parseDoctype parses the data from a DoctypeToken into a name, +// public identifier, and system identifier. It returns a Node whose Type +// is DoctypeNode, whose Data is the name, and which has attributes +// named "system" and "public" for the two identifiers if they were present. +func parseDoctype(s string) *Node { + n := &Node{Type: DoctypeNode} + + // Find the name. + space := strings.IndexAny(s, whitespace) + if space == -1 { + space = len(s) + } + n.Data = strings.ToLower(s[:space]) + s = strings.TrimLeft(s[space:], whitespace) + + if len(s) < 6 { + // It can't start with "PUBLIC" or "SYSTEM". + // Ignore the rest of the string. + return n + } + + key := strings.ToLower(s[:6]) + s = s[6:] + for key == "public" || key == "system" { + s = strings.TrimLeft(s, whitespace) + if s == "" { + break + } + quote := s[0] + if quote != '"' && quote != '\'' { + break + } + s = s[1:] + q := strings.IndexRune(s, rune(quote)) + var id string + if q == -1 { + id = s + s = "" + } else { + id = s[:q] + s = s[q+1:] + } + n.Attr = append(n.Attr, Attribute{Key: key, Val: id}) + if key == "public" { + key = "system" + } else { + key = "" + } + } + + return n +} + // Section 11.2.5.4.1. func initialIM(p *parser) bool { switch p.tok.Type { @@ -337,10 +390,7 @@ func initialIM(p *parser) bool { }) return true case DoctypeToken: - p.doc.Add(&Node{ - Type: DoctypeNode, - Data: p.tok.Data, - }) + p.doc.Add(parseDoctype(p.tok.Data)) p.im = beforeHTMLIM return true } diff --git a/src/pkg/html/parse_test.go b/src/pkg/html/parse_test.go index c1347c9dc1..90d3f46c61 100644 --- a/src/pkg/html/parse_test.go +++ b/src/pkg/html/parse_test.go @@ -97,7 +97,23 @@ func dumpLevel(w io.Writer, n *Node, level int) error { case CommentNode: fmt.Fprintf(w, "", n.Data) case DoctypeNode: - fmt.Fprintf(w, "", n.Data) + fmt.Fprintf(w, "") case scopeMarkerNode: return errors.New("unexpected scopeMarkerNode") default: @@ -133,8 +149,9 @@ func TestParser(t *testing.T) { n int }{ // TODO(nigeltao): Process all the test cases from all the .dat files. + {"doctype01.dat", -1}, {"tests1.dat", -1}, - {"tests2.dat", 59}, + {"tests2.dat", -1}, {"tests3.dat", 0}, } for _, tf := range testFiles { diff --git a/src/pkg/html/render.go b/src/pkg/html/render.go index 92c349fb32..57d78beef1 100644 --- a/src/pkg/html/render.go +++ b/src/pkg/html/render.go @@ -9,6 +9,7 @@ import ( "errors" "fmt" "io" + "strings" ) type writer interface { @@ -98,6 +99,40 @@ func render1(w writer, n *Node) error { if _, err := w.WriteString(n.Data); err != nil { return err } + if n.Attr != nil { + var p, s string + for _, a := range n.Attr { + switch a.Key { + case "public": + p = a.Val + case "system": + s = a.Val + } + } + if p != "" { + if _, err := w.WriteString(" PUBLIC "); err != nil { + return err + } + if err := writeQuoted(w, p); err != nil { + return err + } + if s != "" { + if err := w.WriteByte(' '); err != nil { + return err + } + if err := writeQuoted(w, s); err != nil { + return err + } + } + } else if s != "" { + if _, err := w.WriteString(" SYSTEM "); err != nil { + return err + } + if err := writeQuoted(w, s); err != nil { + return err + } + } + } return w.WriteByte('>') default: return errors.New("html: unknown node type") @@ -181,6 +216,27 @@ func render1(w writer, n *Node) error { return w.WriteByte('>') } +// writeQuoted writes s to w surrounded by quotes. Normally it will use double +// quotes, but if s contains a double quote, it will use single quotes. +// It is used for writing the identifiers in a doctype declaration. +// In valid HTML, they can't contain both types of quotes. +func writeQuoted(w writer, s string) error { + var q byte = '"' + if strings.Contains(s, `"`) { + q = '\'' + } + if err := w.WriteByte(q); err != nil { + return err + } + if _, err := w.WriteString(s); err != nil { + return err + } + if err := w.WriteByte(q); err != nil { + return err + } + return nil +} + // Section 13.1.2, "Elements", gives this list of void elements. Void elements // are those that can't have any contents. var voidElements = map[string]bool{ -- 2.48.1