summaryrefslogtreecommitdiff
path: root/internal/text
diff options
context:
space:
mode:
authorLibravatar kim <89579420+NyaaaWhatsUpDoc@users.noreply.github.com>2022-05-07 16:55:27 +0100
committerLibravatar GitHub <noreply@github.com>2022-05-07 17:55:27 +0200
commit26b74aefaf5d2a3cd26bd57652fe96a6a20ed034 (patch)
treedb316febba8e0ada7a9360b059011dcc7ea138a3 /internal/text
parent[performance] improved logrus output switching performance (#544) (diff)
downloadgotosocial-26b74aefaf5d2a3cd26bd57652fe96a6a20ed034.tar.xz
[bugfix] Fix existing bio text showing as HTML (#531)
* fix existing bio text showing as HTML - updated replaced mentions to include instance - strips HTML from account source note in Verify handler - update text formatter to use buffers for string writes Signed-off-by: kim <grufwub@gmail.com> * go away linter Signed-off-by: kim <grufwub@gmail.com> * change buf reset location, change html mention tags Signed-off-by: kim <grufwub@gmail.com> * reduce FindLinks code complexity Signed-off-by: kim <grufwub@gmail.com> * fix HTML to text conversion Signed-off-by: kim <grufwub@gmail.com> * Update internal/regexes/regexes.go Co-authored-by: Mina Galić <mina.galic@puppet.com> * use improved html2text lib with more options Signed-off-by: kim <grufwub@gmail.com> * fix to produce actual plaintext from html Signed-off-by: kim <grufwub@gmail.com> * fix span tags instead written as space Signed-off-by: kim <grufwub@gmail.com> * performance improvements to regex replacements, fix link replace logic for un-html-ing in the future Signed-off-by: kim <grufwub@gmail.com> * fix tag/mention replacements to use input string, fix link replace to not include scheme Signed-off-by: kim <grufwub@gmail.com> * use matched input string for link replace href text Signed-off-by: kim <grufwub@gmail.com> * remove unused code (to appease linter :sobs:) Signed-off-by: kim <grufwub@gmail.com> * improve hashtagFinger regex to be more compliant Signed-off-by: kim <grufwub@gmail.com> * update breakReplacer to include both unix and windows line endings Signed-off-by: kim <grufwub@gmail.com> * add NoteRaw field to Account to store plaintext account bio, add migration for this, set for sensitive accounts Signed-off-by: kim <grufwub@gmail.com> * drop unnecessary code Signed-off-by: kim <grufwub@gmail.com> * update text package tests to fix logic changes Signed-off-by: kim <grufwub@gmail.com> * add raw note content testing to account update and account verify Signed-off-by: kim <grufwub@gmail.com> * remove unused modules Signed-off-by: kim <grufwub@gmail.com> * fix emoji regex Signed-off-by: kim <grufwub@gmail.com> * fix replacement of hashtags Signed-off-by: kim <grufwub@gmail.com> * update code comment Signed-off-by: kim <grufwub@gmail.com> Co-authored-by: Mina Galić <mina.galic@puppet.com>
Diffstat (limited to 'internal/text')
-rw-r--r--internal/text/common.go61
-rw-r--r--internal/text/link.go84
-rw-r--r--internal/text/link_test.go12
-rw-r--r--internal/text/plain.go11
-rw-r--r--internal/text/plain_test.go2
5 files changed, 73 insertions, 97 deletions
diff --git a/internal/text/common.go b/internal/text/common.go
index 4148ece15..12c0f1dfa 100644
--- a/internal/text/common.go
+++ b/internal/text/common.go
@@ -19,10 +19,11 @@
package text
import (
+ "bytes"
"context"
- "fmt"
"html"
"strings"
+ "unicode"
"github.com/sirupsen/logrus"
@@ -63,38 +64,40 @@ func postformat(in string) string {
}
func (f *formatter) ReplaceTags(ctx context.Context, in string, tags []*gtsmodel.Tag) string {
- return regexes.HashtagFinder.ReplaceAllStringFunc(in, func(match string) string {
+ return regexes.ReplaceAllStringFunc(regexes.HashtagFinder, in, func(match string, buf *bytes.Buffer) string {
// we have a match
matchTrimmed := strings.TrimSpace(match)
- tagAsEntered := strings.Split(matchTrimmed, "#")[1]
+ tagAsEntered := matchTrimmed[1:]
// check through the tags to find what we're matching
for _, tag := range tags {
-
- if strings.EqualFold(matchTrimmed, fmt.Sprintf("#%s", tag.Name)) {
- // replace the #tag with the formatted tag content
- tagContent := fmt.Sprintf(`<a href="%s" class="mention hashtag" rel="tag">#<span>%s</span></a>`, tag.URL, tagAsEntered)
-
- // in case the match picked up any previous space or newlines (thanks to the regex), include them as well
- if strings.HasPrefix(match, " ") {
- tagContent = " " + tagContent
- } else if strings.HasPrefix(match, "\n") {
- tagContent = "\n" + tagContent
+ if strings.EqualFold(tagAsEntered, tag.Name) {
+ // Add any dropped space from match
+ if unicode.IsSpace(rune(match[0])) {
+ buf.WriteByte(match[0])
}
- // done
- return tagContent
+ // replace the #tag with the formatted tag content
+ // `<a href="tag.URL" class="mention hashtag" rel="tag">#<span>tagAsEntered</span></a>
+ buf.WriteString(`<a href="`)
+ buf.WriteString(tag.URL)
+ buf.WriteString(`" class="mention hashtag" rel="tag">#<span>`)
+ buf.WriteString(tagAsEntered)
+ buf.WriteString(`</span></a>`)
+ return buf.String()
}
}
+
// the match wasn't in the list of tags for whatever reason, so just return the match as we found it so nothing changes
return match
})
}
func (f *formatter) ReplaceMentions(ctx context.Context, in string, mentions []*gtsmodel.Mention) string {
- return regexes.MentionFinder.ReplaceAllStringFunc(in, func(match string) string {
- // we have a match
+ return regexes.ReplaceAllStringFunc(regexes.MentionFinder, in, func(match string, buf *bytes.Buffer) string {
+ // we have a match, trim any spaces
matchTrimmed := strings.TrimSpace(match)
+
// check through mentions to find what we're matching
for _, menchie := range mentions {
if strings.EqualFold(matchTrimmed, menchie.NameString) {
@@ -107,22 +110,26 @@ func (f *formatter) ReplaceMentions(ctx context.Context, in string, mentions []*
}
menchie.TargetAccount = a
}
- targetAccount := menchie.TargetAccount
- // replace the mention with the formatted mention content
- mentionContent := fmt.Sprintf(`<span class="h-card"><a href="%s" class="u-url mention">@<span>%s</span></a></span>`, targetAccount.URL, targetAccount.Username)
+ // The mention's target is our target
+ targetAccount := menchie.TargetAccount
- // in case the match picked up any previous space or newlines (thanks to the regex), include them as well
- if strings.HasPrefix(match, " ") {
- mentionContent = " " + mentionContent
- } else if strings.HasPrefix(match, "\n") {
- mentionContent = "\n" + mentionContent
+ // Add any dropped space from match
+ if unicode.IsSpace(rune(match[0])) {
+ buf.WriteByte(match[0])
}
- // done
- return mentionContent
+ // replace the mention with the formatted mention content
+ // <span class="h-card"><a href="targetAccount.URL" class="u-url mention">@<span>targetAccount.Username</span></a></span>
+ buf.WriteString(`<span class="h-card"><a href="`)
+ buf.WriteString(targetAccount.URL)
+ buf.WriteString(`" class="u-url mention">@<span>`)
+ buf.WriteString(targetAccount.Username)
+ buf.WriteString(`</span></a></span>`)
+ return buf.String()
}
}
+
// the match wasn't in the list of mentions for whatever reason, so just return the match as we found it so nothing changes
return match
})
diff --git a/internal/text/link.go b/internal/text/link.go
index d8d83df6d..f72c451f2 100644
--- a/internal/text/link.go
+++ b/internal/text/link.go
@@ -19,34 +19,28 @@
package text
import (
+ "bytes"
"context"
- "fmt"
"net/url"
+ "strings"
- "mvdan.cc/xurls/v2"
+ "github.com/superseriousbusiness/gotosocial/internal/regexes"
)
-// schemes is the regex for schemes we accept when looking for links.
-// Basically, we accept https or http.
-var schemes = `(((http|https))://)`
-
// FindLinks parses the given string looking for recognizable URLs (including scheme).
// It returns a list of those URLs, without changing the string, or an error if something goes wrong.
// If no URLs are found within the given string, an empty slice and nil will be returned.
-func FindLinks(in string) ([]*url.URL, error) {
- rxStrict, err := xurls.StrictMatchingScheme(schemes)
- if err != nil {
- return nil, err
- }
-
- urls := []*url.URL{}
+func FindLinks(in string) []*url.URL {
+ var urls []*url.URL
// bail already if we don't find anything
- found := rxStrict.FindAllString(in, -1)
+ found := regexes.LinkScheme.FindAllString(in, -1)
if len(found) == 0 {
- return urls, nil
+ return nil
}
+ urlmap := map[string]struct{}{}
+
// for each string we find, we want to parse it into a URL if we can
// if we fail to parse it, just ignore this match and continue
for _, f := range found {
@@ -54,29 +48,18 @@ func FindLinks(in string) ([]*url.URL, error) {
if err != nil {
continue
}
- urls = append(urls, u)
- }
- // deduplicate the URLs
- urlsDeduped := []*url.URL{}
+ // Calculate string
+ ustr := u.String()
- for _, u := range urls {
- if !contains(urlsDeduped, u) {
- urlsDeduped = append(urlsDeduped, u)
+ if _, ok := urlmap[ustr]; !ok {
+ // Has not been encountered yet
+ urls = append(urls, u)
+ urlmap[ustr] = struct{}{}
}
}
- return urlsDeduped, nil
-}
-
-// contains checks if the given url is already within a slice of URLs
-func contains(urls []*url.URL, url *url.URL) bool {
- for _, u := range urls {
- if u.String() == url.String() {
- return true
- }
- }
- return false
+ return urls
}
// ReplaceLinks replaces all detected links in a piece of text with their HTML (href) equivalents.
@@ -84,33 +67,20 @@ func contains(urls []*url.URL, url *url.URL) bool {
// href will end up double-formatted, if the text you pass here contains one or more hrefs already.
// To avoid this, you should sanitize any HTML out of text before you pass it into this function.
func (f *formatter) ReplaceLinks(ctx context.Context, in string) string {
- rxStrict, err := xurls.StrictMatchingScheme(schemes)
- if err != nil {
- panic(err)
- }
-
- replaced := rxStrict.ReplaceAllStringFunc(in, func(urlString string) string {
+ return regexes.ReplaceAllStringFunc(regexes.LinkScheme, in, func(urlString string, buf *bytes.Buffer) string {
thisURL, err := url.Parse(urlString)
if err != nil {
return urlString // we can't parse it as a URL so don't replace it
}
-
- shortString := thisURL.Hostname()
-
- if thisURL.Path != "" {
- shortString += thisURL.Path
- }
-
- if thisURL.Fragment != "" {
- shortString = shortString + "#" + thisURL.Fragment
- }
-
- if thisURL.RawQuery != "" {
- shortString = shortString + "?" + thisURL.RawQuery
- }
-
- replacement := fmt.Sprintf(`<a href="%s" rel="noopener">%s</a>`, urlString, shortString)
- return replacement
+ // <a href="thisURL.String()" rel="noopener">urlString</a>
+ urlString = thisURL.String()
+ buf.WriteString(`<a href="`)
+ buf.WriteString(thisURL.String())
+ buf.WriteString(`" rel="noopener">`)
+ urlString = strings.TrimPrefix(urlString, thisURL.Scheme)
+ urlString = strings.TrimPrefix(urlString, "://")
+ buf.WriteString(urlString)
+ buf.WriteString(`</a>`)
+ return buf.String()
})
- return replaced
}
diff --git a/internal/text/link_test.go b/internal/text/link_test.go
index e524315e7..24484e02d 100644
--- a/internal/text/link_test.go
+++ b/internal/text/link_test.go
@@ -75,9 +75,7 @@ func (suite *LinkTestSuite) TestParseSimple() {
}
func (suite *LinkTestSuite) TestParseURLsFromText1() {
- urls, err := text.FindLinks(text1)
-
- assert.NoError(suite.T(), err)
+ urls := text.FindLinks(text1)
assert.Equal(suite.T(), "https://example.org/link/to/something#fragment", urls[0].String())
assert.Equal(suite.T(), "http://test.example.org?q=bahhhhhhhhhhhh", urls[1].String())
@@ -86,16 +84,14 @@ func (suite *LinkTestSuite) TestParseURLsFromText1() {
}
func (suite *LinkTestSuite) TestParseURLsFromText2() {
- urls, err := text.FindLinks(text2)
- assert.NoError(suite.T(), err)
+ urls := text.FindLinks(text2)
// assert length 1 because the found links will be deduplicated
assert.Len(suite.T(), urls, 1)
}
func (suite *LinkTestSuite) TestParseURLsFromText3() {
- urls, err := text.FindLinks(text3)
- assert.NoError(suite.T(), err)
+ urls := text.FindLinks(text3)
// assert length 0 because `mailto:` isn't accepted
assert.Len(suite.T(), urls, 0)
@@ -112,7 +108,7 @@ Here's link number two: <a href="http://test.example.org?q=bahhhhhhhhhhhh" rel="
really.cool.website <-- this one shouldn't be parsed as a link because it doesn't contain the scheme
-<a href="https://example.orghttps://google.com" rel="noopener">example.orghttps//google.com</a> <-- this shouldn't work either, but it does?! OK
+<a href="https://example.orghttps://google.com" rel="noopener">example.orghttps://google.com</a> <-- this shouldn't work either, but it does?! OK
`, replaced)
}
diff --git a/internal/text/plain.go b/internal/text/plain.go
index 453f4dd31..4ef3b3715 100644
--- a/internal/text/plain.go
+++ b/internal/text/plain.go
@@ -20,12 +20,17 @@ package text
import (
"context"
- "fmt"
"strings"
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
)
+// breakReplacer replaces new-lines with HTML breaks.
+var breakReplacer = strings.NewReplacer(
+ "\r\n", "<br/>",
+ "\n", "<br/>",
+)
+
func (f *formatter) FromPlain(ctx context.Context, plain string, mentions []*gtsmodel.Mention, tags []*gtsmodel.Tag) string {
content := preformat(plain)
@@ -42,10 +47,10 @@ func (f *formatter) FromPlain(ctx context.Context, plain string, mentions []*gts
content = f.ReplaceMentions(ctx, content, mentions)
// replace newlines with breaks
- content = strings.ReplaceAll(content, "\n", "<br />")
+ content = breakReplacer.Replace(content)
// wrap the whole thing in a pee
- content = fmt.Sprintf(`<p>%s</p>`, content)
+ content = `<p>` + content + `</p>`
return postformat(content)
}
diff --git a/internal/text/plain_test.go b/internal/text/plain_test.go
index d8b7c17da..2b7b50d5e 100644
--- a/internal/text/plain_test.go
+++ b/internal/text/plain_test.go
@@ -53,7 +53,6 @@ func (suite *PlainTestSuite) TestParseSimple() {
}
func (suite *PlainTestSuite) TestParseWithTag() {
-
foundTags := []*gtsmodel.Tag{
suite.testTags["welcome"],
}
@@ -63,7 +62,6 @@ func (suite *PlainTestSuite) TestParseWithTag() {
}
func (suite *PlainTestSuite) TestParseMoreComplex() {
-
foundTags := []*gtsmodel.Tag{
suite.testTags["Hashtag"],
}