patch of appview/pages/markup: move sanitizer to separate file · round #0 · pull #500 · tangled.org/core

-83

appview/pages/markup/markdown.go

···

       5
       5
        
       	"bytes"

     

       6
       6
        
       	"fmt"

     

       7
       7
        
       	"io"

     

       8
       8
       -
       	"maps"

     

       9
       8
        
       	"net/url"

     

       10
       9
        
       	"path"

     

       11
       11
       -
       	"regexp"

     

       12
       12
       -
       	"slices"

     

       13
       10
        
       	"strings"

     

       14
       11
        
       

     

       15
       15
       -
       	"github.com/alecthomas/chroma/v2"

     

       16
       12
        
       	chromahtml "github.com/alecthomas/chroma/v2/formatters/html"

     

       17
       13
        
       	"github.com/alecthomas/chroma/v2/styles"

     

       18
       18
       -
       	"github.com/microcosm-cc/bluemonday"

     

       19
       14
        
       	"github.com/yuin/goldmark"

     

       20
       15
        
       	highlighting "github.com/yuin/goldmark-highlighting/v2"

     

       21
       16
        
       	"github.com/yuin/goldmark/ast"

     
···

       50
       45
        
       	Sanitizer    Sanitizer

     

       51
       46
        
       }

     

       52
       47
        
       

     

       53
       53
       -
       type Sanitizer struct {

     

       54
       54
       -
       	defaultPolicy *bluemonday.Policy

     

       55
       55
       -
       }

     

       56
       56
       -
       

     

       57
       48
        
       func (rctx *RenderContext) RenderMarkdown(source string) string {

     

       58
       49
        
       	md := goldmark.New(

     

       59
       50
        
       		goldmark.WithExtensions(

     
···

       170
       161
        
       	return rctx.Sanitizer.defaultPolicy.Sanitize(html)

     

       171
       162
        
       }

     

       172
       163
        
       

     

       173
       173
       -
       func NewSanitizer() Sanitizer {

     

       174
       174
       -
       	return Sanitizer{

     

       175
       175
       -
       		defaultPolicy: defaultPolicy(),

     

       176
       176
       -
       	}

     

       177
       177
       -
       }

     

       178
       178
       -
       func defaultPolicy() *bluemonday.Policy {

     

       179
       179
       -
       	policy := bluemonday.UGCPolicy()

     

       180
       180
       -
       

     

       181
       181
       -
       	// Allow generally safe attributes

     

       182
       182
       -
       	generalSafeAttrs := []string{

     

       183
       183
       -
       		"abbr", "accept", "accept-charset",

     

       184
       184
       -
       		"accesskey", "action", "align", "alt",

     

       185
       185
       -
       		"aria-describedby", "aria-hidden", "aria-label", "aria-labelledby",

     

       186
       186
       -
       		"axis", "border", "cellpadding", "cellspacing", "char",

     

       187
       187
       -
       		"charoff", "charset", "checked",

     

       188
       188
       -
       		"clear", "cols", "colspan", "color",

     

       189
       189
       -
       		"compact", "coords", "datetime", "dir",

     

       190
       190
       -
       		"disabled", "enctype", "for", "frame",

     

       191
       191
       -
       		"headers", "height", "hreflang",

     

       192
       192
       -
       		"hspace", "ismap", "label", "lang",

     

       193
       193
       -
       		"maxlength", "media", "method",

     

       194
       194
       -
       		"multiple", "name", "nohref", "noshade",

     

       195
       195
       -
       		"nowrap", "open", "prompt", "readonly", "rel", "rev",

     

       196
       196
       -
       		"rows", "rowspan", "rules", "scope",

     

       197
       197
       -
       		"selected", "shape", "size", "span",

     

       198
       198
       -
       		"start", "summary", "tabindex", "target",

     

       199
       199
       -
       		"title", "type", "usemap", "valign", "value",

     

       200
       200
       -
       		"vspace", "width", "itemprop",

     

       201
       201
       -
       	}

     

       202
       202
       -
       

     

       203
       203
       -
       	generalSafeElements := []string{

     

       204
       204
       -
       		"h1", "h2", "h3", "h4", "h5", "h6", "h7", "h8", "br", "b", "i", "strong", "em", "a", "pre", "code", "img", "tt",

     

       205
       205
       -
       		"div", "ins", "del", "sup", "sub", "p", "ol", "ul", "table", "thead", "tbody", "tfoot", "blockquote", "label",

     

       206
       206
       -
       		"dl", "dt", "dd", "kbd", "q", "samp", "var", "hr", "ruby", "rt", "rp", "li", "tr", "td", "th", "s", "strike", "summary",

     

       207
       207
       -
       		"details", "caption", "figure", "figcaption",

     

       208
       208
       -
       		"abbr", "bdo", "cite", "dfn", "mark", "small", "span", "time", "video", "wbr",

     

       209
       209
       -
       	}

     

       210
       210
       -
       

     

       211
       211
       -
       	policy.AllowAttrs(generalSafeAttrs...).OnElements(generalSafeElements...)

     

       212
       212
       -
       

     

       213
       213
       -
       	// video

     

       214
       214
       -
       	policy.AllowAttrs("src", "autoplay", "controls").OnElements("video")

     

       215
       215
       -
       

     

       216
       216
       -
       	// checkboxes

     

       217
       217
       -
       	policy.AllowAttrs("type").Matching(regexp.MustCompile(`^checkbox$`)).OnElements("input")

     

       218
       218
       -
       	policy.AllowAttrs("checked", "disabled", "data-source-position").OnElements("input")

     

       219
       219
       -
       

     

       220
       220
       -
       	// for code blocks

     

       221
       221
       -
       	policy.AllowAttrs("class").Matching(regexp.MustCompile(`chroma`)).OnElements("pre")

     

       222
       222
       -
       	policy.AllowAttrs("class").Matching(regexp.MustCompile(strings.Join(slices.Collect(maps.Values(chroma.StandardTypes)), "|"))).OnElements("span")

     

       223
       223
       -
       

     

       224
       224
       -
       	// centering content

     

       225
       225
       -
       	policy.AllowElements("center")

     

       226
       226
       -
       

     

       227
       227
       -
       	policy.AllowAttrs("align", "style", "width", "height").Globally()

     

       228
       228
       -
       	policy.AllowStyles(

     

       229
       229
       -
       		"margin",

     

       230
       230
       -
       		"padding",

     

       231
       231
       -
       		"text-align",

     

       232
       232
       -
       		"font-weight",

     

       233
       233
       -
       		"text-decoration",

     

       234
       234
       -
       		"padding-left",

     

       235
       235
       -
       		"padding-right",

     

       236
       236
       -
       		"padding-top",

     

       237
       237
       -
       		"padding-bottom",

     

       238
       238
       -
       		"margin-left",

     

       239
       239
       -
       		"margin-right",

     

       240
       240
       -
       		"margin-top",

     

       241
       241
       -
       		"margin-bottom",

     

       242
       242
       -
       	)

     

       243
       243
       -
       

     

       244
       244
       -
       	return policy

     

       245
       245
       -
       }

     

       246
       246
       -
       

     

       247
       164
        
       type MarkdownTransformer struct {

     

       248
       165
        
       	rctx *RenderContext

     

       249
       166
        
       }

+90

appview/pages/markup/sanitizer.go

···

       1
       1
       +
       package markup

     

       2
       2
       +
       

     

       3
       3
       +
       import (

     

       4
       4
       +
       	"maps"

     

       5
       5
       +
       	"regexp"

     

       6
       6
       +
       	"slices"

     

       7
       7
       +
       	"strings"

     

       8
       8
       +
       

     

       9
       9
       +
       	"github.com/alecthomas/chroma/v2"

     

       10
       10
       +
       	"github.com/microcosm-cc/bluemonday"

     

       11
       11
       +
       )

     

       12
       12
       +
       

     

       13
       13
       +
       type Sanitizer struct {

     

       14
       14
       +
       	defaultPolicy *bluemonday.Policy

     

       15
       15
       +
       }

     

       16
       16
       +
       

     

       17
       17
       +
       func NewSanitizer() Sanitizer {

     

       18
       18
       +
       	return Sanitizer{

     

       19
       19
       +
       		defaultPolicy: defaultPolicy(),

     

       20
       20
       +
       	}

     

       21
       21
       +
       }

     

       22
       22
       +
       

     

       23
       23
       +
       func defaultPolicy() *bluemonday.Policy {

     

       24
       24
       +
       	policy := bluemonday.UGCPolicy()

     

       25
       25
       +
       

     

       26
       26
       +
       	// Allow generally safe attributes

     

       27
       27
       +
       	generalSafeAttrs := []string{

     

       28
       28
       +
       		"abbr", "accept", "accept-charset",

     

       29
       29
       +
       		"accesskey", "action", "align", "alt",

     

       30
       30
       +
       		"aria-describedby", "aria-hidden", "aria-label", "aria-labelledby",

     

       31
       31
       +
       		"axis", "border", "cellpadding", "cellspacing", "char",

     

       32
       32
       +
       		"charoff", "charset", "checked",

     

       33
       33
       +
       		"clear", "cols", "colspan", "color",

     

       34
       34
       +
       		"compact", "coords", "datetime", "dir",

     

       35
       35
       +
       		"disabled", "enctype", "for", "frame",

     

       36
       36
       +
       		"headers", "height", "hreflang",

     

       37
       37
       +
       		"hspace", "ismap", "label", "lang",

     

       38
       38
       +
       		"maxlength", "media", "method",

     

       39
       39
       +
       		"multiple", "name", "nohref", "noshade",

     

       40
       40
       +
       		"nowrap", "open", "prompt", "readonly", "rel", "rev",

     

       41
       41
       +
       		"rows", "rowspan", "rules", "scope",

     

       42
       42
       +
       		"selected", "shape", "size", "span",

     

       43
       43
       +
       		"start", "summary", "tabindex", "target",

     

       44
       44
       +
       		"title", "type", "usemap", "valign", "value",

     

       45
       45
       +
       		"vspace", "width", "itemprop",

     

       46
       46
       +
       	}

     

       47
       47
       +
       

     

       48
       48
       +
       	generalSafeElements := []string{

     

       49
       49
       +
       		"h1", "h2", "h3", "h4", "h5", "h6", "h7", "h8", "br", "b", "i", "strong", "em", "a", "pre", "code", "img", "tt",

     

       50
       50
       +
       		"div", "ins", "del", "sup", "sub", "p", "ol", "ul", "table", "thead", "tbody", "tfoot", "blockquote", "label",

     

       51
       51
       +
       		"dl", "dt", "dd", "kbd", "q", "samp", "var", "hr", "ruby", "rt", "rp", "li", "tr", "td", "th", "s", "strike", "summary",

     

       52
       52
       +
       		"details", "caption", "figure", "figcaption",

     

       53
       53
       +
       		"abbr", "bdo", "cite", "dfn", "mark", "small", "span", "time", "video", "wbr",

     

       54
       54
       +
       	}

     

       55
       55
       +
       

     

       56
       56
       +
       	policy.AllowAttrs(generalSafeAttrs...).OnElements(generalSafeElements...)

     

       57
       57
       +
       

     

       58
       58
       +
       	// video

     

       59
       59
       +
       	policy.AllowAttrs("src", "autoplay", "controls").OnElements("video")

     

       60
       60
       +
       

     

       61
       61
       +
       	// checkboxes

     

       62
       62
       +
       	policy.AllowAttrs("type").Matching(regexp.MustCompile(`^checkbox$`)).OnElements("input")

     

       63
       63
       +
       	policy.AllowAttrs("checked", "disabled", "data-source-position").OnElements("input")

     

       64
       64
       +
       

     

       65
       65
       +
       	// for code blocks

     

       66
       66
       +
       	policy.AllowAttrs("class").Matching(regexp.MustCompile(`chroma`)).OnElements("pre")

     

       67
       67
       +
       	policy.AllowAttrs("class").Matching(regexp.MustCompile(strings.Join(slices.Collect(maps.Values(chroma.StandardTypes)), "|"))).OnElements("span")

     

       68
       68
       +
       

     

       69
       69
       +
       	// centering content

     

       70
       70
       +
       	policy.AllowElements("center")

     

       71
       71
       +
       

     

       72
       72
       +
       	policy.AllowAttrs("align", "style", "width", "height").Globally()

     

       73
       73
       +
       	policy.AllowStyles(

     

       74
       74
       +
       		"margin",

     

       75
       75
       +
       		"padding",

     

       76
       76
       +
       		"text-align",

     

       77
       77
       +
       		"font-weight",

     

       78
       78
       +
       		"text-decoration",

     

       79
       79
       +
       		"padding-left",

     

       80
       80
       +
       		"padding-right",

     

       81
       81
       +
       		"padding-top",

     

       82
       82
       +
       		"padding-bottom",

     

       83
       83
       +
       		"margin-left",

     

       84
       84
       +
       		"margin-right",

     

       85
       85
       +
       		"margin-top",

     

       86
       86
       +
       		"margin-bottom",

     

       87
       87
       +
       	)

     

       88
       88
       +
       

     

       89
       89
       +
       	return policy

     

       90
       90
       +
       }