summaryrefslogtreecommitdiff
path: root/unxml.go
blob: a312410ee1b97df8736b8a0fdc64b8ea5e1508ba (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
/* See LICENSE file for copyright and license details. */

package unxml

import (
	"fmt"
	"io"
	"os"

	"golang.org/x/net/html"
)

type Reader struct {
	reader    io.Reader
	tagmap    map[string]bool
	lastread  []byte
	count     int
	tokenizer *html.Tokenizer
}

type ElementReader struct {
	xr          Reader
	tagsinstack map[string]int
	intagtokeep bool
}

//type stack []string
//
//func (s stack) Empty() bool  { return len(s) == 0 }
//func (s stack) Peek() string { return s[len(s)-1] }
//func (s *stack) Pop() string {
//	d := (*s)[len(*s)-1]
//	(*s) = (*s)[:len(*s)-1]
//	return d
//}

func NewReaderKeepTags(r io.Reader, tagstokeep []string) *Reader {
	var tagmap map[string]bool

	if len(tagstokeep) > 0 {
		tagmap = make(map[string]bool, 10)
		for _, tag := range tagstokeep {
			tagmap[tag] = true
		}
	} else {
		tagmap = nil
	}

	return &Reader{reader: r,
		tagmap:    tagmap,
		tokenizer: html.NewTokenizer(r),
	}
}

func NewReaderKeepElements(r io.Reader, tagstokeep []string) *ElementReader {
	var tagmap map[string]bool

	if len(tagstokeep) > 0 {
		tagmap = make(map[string]bool, 10)
		for _, tag := range tagstokeep {
			tagmap[tag] = true
		}
	} else {
		tagmap = nil
	}

	return &ElementReader{
		xr: Reader{
			tagmap:    tagmap,
			tokenizer: html.NewTokenizer(r),
		},
		tagsinstack: make(map[string]int, 5),
	}
}

func (r *Reader) Read(out []byte) (int, error) {
	var err error

	r.count = 0
	n := 0
	lenout := len(out)
	if lenout == 0 {
		return r.count, nil
	}

	lenlr := len(r.lastread)
	if lenlr > 0 {
		n = copy(out[0:], r.lastread)
		r.count += n
		r.lastread = make([]byte, len(out))
		lenout -= n
	}

	for {
		tt := r.tokenizer.Next()

		switch tt {
		case html.ErrorToken:
			return r.count, io.EOF

		case html.TextToken:
			text := r.tokenizer.Text()
			lentext := len(text)
			if lentext <= lenout {
				n = copy(out[r.count:], text)
				r.count += n
				lenout -= n
			} else {
				n = copy(out[r.count:], text[:lenout-1])
				r.count += n
				r.lastread = text[lenout-1:]
				return r.count, err
			}

		case html.StartTagToken:
			tn, _ := r.tokenizer.TagName()
			if _, ok := r.tagmap[string(tn)]; ok {
			}
			//fmt.Printf("TagName: %s\n", tn)

		case html.EndTagToken:
			_, _ = r.tokenizer.TagName()
			//fmt.Printf("TagEndName: %s\n", tn)
		}
	}
}

func (r *ElementReader) Read(out []byte) (int, error) {
	var err error

	r.xr.count = 0
	n := 0
	lenout := len(out)
	if lenout == 0 {
		return r.xr.count, nil
	}

	lenlr := len(r.xr.lastread)
	if lenlr > 0 {
		if lenlr < lenout {
			//fmt.Printf("Using lastread: %q\n", r.xr.lastread)
			n = copy(out[0:], r.xr.lastread)
			r.xr.count += n
			lenout -= n
			r.xr.lastread = make([]byte, 0, lenout)
		} else {
			//fmt.Printf("Using lastread not enough: %q\n", r.xr.lastread)
			n = copy(out[0:], r.xr.lastread[:lenout])
			r.xr.lastread = r.xr.lastread[lenout:]
			return n, err
		}
	}

	for {
		tt := r.xr.tokenizer.Next()

		switch tt {
		case html.ErrorToken:
			fmt.Fprintf(os.Stderr, "There was an error when parsing the html: %s, %s\n", tt, r.xr.tokenizer.Err())
			return r.xr.count, io.EOF

		case html.TextToken:
			if !r.intagtokeep {
				continue
			}
			text := r.xr.tokenizer.Text()
			//fmt.Printf("HAD SPACE: %q, count: %d\n", text, r.xr.count)
			n = copy(out[r.xr.count:], text)
			r.xr.count += n
			lenout -= n
			if n < len(text) {
				//fmt.Printf("HAD NO SPACE: wrote: %q, count: %d, lenout: %d\n", text[:lenout], r.xr.count, lenout)
				r.xr.lastread = text[n:]
				//fmt.Printf("lastread is now: %q\n", text[lenout:])
				return r.xr.count, err
			}

		case html.StartTagToken:
			tn, _ := r.xr.tokenizer.TagName()
			//fmt.Printf("TagNameStart: %s\n", tn)
			if _, ok := r.xr.tagmap[string(tn)]; ok {
				r.tagsinstack[string(tn)]++
				r.intagtokeep = true
				raw := r.xr.tokenizer.Raw()
				//fmt.Printf("TokenRaw: %s\n", raw)
				if len(raw) < lenout {
					n := copy(out[r.xr.count:], raw)
					r.xr.count += n
					lenout -= n
				} else {
					n = copy(out[r.xr.count:], raw[:lenout])
					r.xr.count += n
					r.xr.lastread = raw[lenout:]
					return r.xr.count, err
				}
			}

		case html.EndTagToken:
			tn, _ := r.xr.tokenizer.TagName()
			//fmt.Printf("TagEndName: %s\n", tn)
			if count, ok := r.tagsinstack[string(tn)]; ok {
				//fmt.Printf("TagEndNameInStack: %s, %d\n", tn, count)
				if count == 1 {
					delete(r.tagsinstack, string(tn))
					r.intagtokeep = false
				} else {
					r.tagsinstack[string(tn)]--
				}
				raw := r.xr.tokenizer.Raw()
				if len(raw) < lenout {
					n := copy(out[r.xr.count:], raw)
					r.xr.count += n
					lenout -= n
				} else {
					n = copy(out[r.xr.count:], raw[:lenout])
					r.xr.count += n
					r.xr.lastread = raw[lenout:]
					return r.xr.count, err
				}
			}
		}
	}
}