2023-03-12 16:00:57 +01:00
|
|
|
// GoToSocial
|
|
|
|
// Copyright (C) GoToSocial Authors admin@gotosocial.org
|
|
|
|
// SPDX-License-Identifier: AGPL-3.0-or-later
|
|
|
|
//
|
|
|
|
// This program is free software: you can redistribute it and/or modify
|
|
|
|
// it under the terms of the GNU Affero 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 Affero General Public License for more details.
|
|
|
|
//
|
|
|
|
// You should have received a copy of the GNU Affero General Public License
|
|
|
|
// along with this program. If not, see <http://www.gnu.org/licenses/>.
|
2021-07-26 20:25:54 +02:00
|
|
|
|
|
|
|
package text
|
|
|
|
|
|
|
|
import (
|
2023-02-03 11:58:58 +01:00
|
|
|
"bytes"
|
2021-08-25 15:34:33 +02:00
|
|
|
"context"
|
2021-07-26 20:25:54 +02:00
|
|
|
|
2023-10-04 14:09:42 +02:00
|
|
|
"codeberg.org/gruf/go-byteutil"
|
2021-07-26 20:25:54 +02:00
|
|
|
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
|
2023-02-03 11:58:58 +01:00
|
|
|
"github.com/superseriousbusiness/gotosocial/internal/log"
|
|
|
|
"github.com/yuin/goldmark"
|
|
|
|
"github.com/yuin/goldmark/extension"
|
|
|
|
"github.com/yuin/goldmark/parser"
|
|
|
|
"github.com/yuin/goldmark/renderer/html"
|
|
|
|
"github.com/yuin/goldmark/util"
|
2021-07-26 20:25:54 +02:00
|
|
|
)
|
|
|
|
|
2023-09-29 10:39:56 +02:00
|
|
|
// FromPlain fulfils FormatFunc by parsing
|
|
|
|
// the given plaintext input into a FormatResult.
|
|
|
|
func (f *Formatter) FromPlain(
|
2023-05-09 12:16:10 +02:00
|
|
|
ctx context.Context,
|
2023-09-29 10:39:56 +02:00
|
|
|
parseMention gtsmodel.ParseMentionFunc,
|
2023-05-09 12:16:10 +02:00
|
|
|
authorID string,
|
|
|
|
statusID string,
|
2023-09-29 10:39:56 +02:00
|
|
|
input string,
|
2023-05-09 12:16:10 +02:00
|
|
|
) *FormatResult {
|
2023-09-29 10:39:56 +02:00
|
|
|
// Initialize standard block parser
|
|
|
|
// that wraps result in <p> tags.
|
|
|
|
plainTextParser := parser.NewParser(
|
|
|
|
parser.WithBlockParsers(
|
|
|
|
util.Prioritized(newPlaintextParser(), 500),
|
2023-02-03 11:58:58 +01:00
|
|
|
),
|
|
|
|
)
|
2021-07-29 13:18:22 +02:00
|
|
|
|
2023-09-29 10:39:56 +02:00
|
|
|
return f.fromPlain(
|
|
|
|
ctx,
|
|
|
|
plainTextParser,
|
|
|
|
false, // emojiOnly = false
|
|
|
|
parseMention,
|
|
|
|
authorID,
|
|
|
|
statusID,
|
|
|
|
input,
|
|
|
|
)
|
|
|
|
}
|
2021-07-26 20:25:54 +02:00
|
|
|
|
2023-09-29 10:39:56 +02:00
|
|
|
// FromPlainNoParagraph fulfils FormatFunc by parsing
|
|
|
|
// the given plaintext input into a FormatResult.
|
|
|
|
//
|
|
|
|
// Unlike FromPlain, it will not wrap the resulting
|
|
|
|
// HTML in <p> tags, making it useful for parsing
|
|
|
|
// short fragments of text that oughtn't be formally
|
|
|
|
// wrapped as a paragraph.
|
|
|
|
func (f *Formatter) FromPlainNoParagraph(
|
|
|
|
ctx context.Context,
|
|
|
|
parseMention gtsmodel.ParseMentionFunc,
|
|
|
|
authorID string,
|
|
|
|
statusID string,
|
|
|
|
input string,
|
|
|
|
) *FormatResult {
|
|
|
|
// Initialize block parser that
|
|
|
|
// doesn't wrap result in <p> tags.
|
|
|
|
plainTextParser := parser.NewParser(
|
|
|
|
parser.WithBlockParsers(
|
|
|
|
util.Prioritized(newPlaintextParserNoParagraph(), 500),
|
|
|
|
),
|
|
|
|
)
|
2021-08-16 19:17:56 +02:00
|
|
|
|
2023-09-29 10:39:56 +02:00
|
|
|
return f.fromPlain(
|
|
|
|
ctx,
|
|
|
|
plainTextParser,
|
|
|
|
false, // emojiOnly = false
|
|
|
|
parseMention,
|
|
|
|
authorID,
|
|
|
|
statusID,
|
|
|
|
input,
|
|
|
|
)
|
2021-07-26 20:25:54 +02:00
|
|
|
}
|
2023-05-09 12:16:10 +02:00
|
|
|
|
2023-09-29 10:39:56 +02:00
|
|
|
// FromPlainEmojiOnly fulfils FormatFunc by parsing
|
|
|
|
// the given plaintext input into a FormatResult.
|
|
|
|
//
|
|
|
|
// Unlike FromPlain, it will only parse emojis with
|
|
|
|
// the custom renderer, leaving aside mentions and tags.
|
|
|
|
func (f *Formatter) FromPlainEmojiOnly(
|
|
|
|
ctx context.Context,
|
|
|
|
parseMention gtsmodel.ParseMentionFunc,
|
|
|
|
authorID string,
|
|
|
|
statusID string,
|
|
|
|
input string,
|
|
|
|
) *FormatResult {
|
2023-10-04 14:09:42 +02:00
|
|
|
// Initialize block parser that
|
|
|
|
// doesn't wrap result in <p> tags.
|
2023-09-29 10:39:56 +02:00
|
|
|
plainTextParser := parser.NewParser(
|
2023-05-09 12:16:10 +02:00
|
|
|
parser.WithBlockParsers(
|
2023-10-04 14:09:42 +02:00
|
|
|
util.Prioritized(newPlaintextParserNoParagraph(), 500),
|
2023-05-09 12:16:10 +02:00
|
|
|
),
|
|
|
|
)
|
|
|
|
|
2023-09-29 10:39:56 +02:00
|
|
|
return f.fromPlain(
|
|
|
|
ctx,
|
|
|
|
plainTextParser,
|
|
|
|
true, // emojiOnly = true
|
|
|
|
parseMention,
|
|
|
|
authorID,
|
|
|
|
statusID,
|
|
|
|
input,
|
|
|
|
)
|
2023-05-09 12:16:10 +02:00
|
|
|
}
|
|
|
|
|
2023-09-29 10:39:56 +02:00
|
|
|
// fromPlain parses the given input text
|
|
|
|
// using the given plainTextParser, and
|
|
|
|
// returns the result.
|
|
|
|
func (f *Formatter) fromPlain(
|
|
|
|
ctx context.Context,
|
|
|
|
plainTextParser parser.Parser,
|
|
|
|
emojiOnly bool,
|
|
|
|
parseMention gtsmodel.ParseMentionFunc,
|
|
|
|
authorID string,
|
|
|
|
statusID string,
|
|
|
|
input string,
|
|
|
|
) *FormatResult {
|
|
|
|
result := new(FormatResult)
|
|
|
|
|
|
|
|
// Instantiate goldmark parser for
|
|
|
|
// plaintext, using custom renderer
|
|
|
|
// to add hashtag/mention links.
|
|
|
|
md := goldmark.New(
|
|
|
|
goldmark.WithRendererOptions(
|
|
|
|
html.WithXHTML(),
|
|
|
|
html.WithHardWraps(),
|
|
|
|
),
|
|
|
|
// Use whichever plaintext
|
|
|
|
// parser we were passed.
|
|
|
|
goldmark.WithParser(plainTextParser),
|
|
|
|
goldmark.WithExtensions(
|
|
|
|
&customRenderer{
|
|
|
|
ctx,
|
|
|
|
f.db,
|
|
|
|
parseMention,
|
|
|
|
authorID,
|
|
|
|
statusID,
|
|
|
|
emojiOnly,
|
|
|
|
result,
|
|
|
|
},
|
|
|
|
extension.Linkify, // Turns URLs into links.
|
2023-05-09 12:16:10 +02:00
|
|
|
),
|
|
|
|
)
|
|
|
|
|
2023-10-04 14:09:42 +02:00
|
|
|
// Convert input string to bytes
|
|
|
|
// without performing any allocs.
|
|
|
|
bInput := byteutil.S2B(input)
|
|
|
|
|
2023-09-29 10:39:56 +02:00
|
|
|
// Parse input into HTML.
|
|
|
|
var htmlBytes bytes.Buffer
|
|
|
|
if err := md.Convert(
|
2023-10-04 14:09:42 +02:00
|
|
|
bInput,
|
2023-09-29 10:39:56 +02:00
|
|
|
&htmlBytes,
|
|
|
|
); err != nil {
|
|
|
|
log.Errorf(ctx, "error formatting plaintext input to HTML: %s", err)
|
|
|
|
}
|
|
|
|
|
|
|
|
// Clean and shrink HTML.
|
2023-10-04 14:09:42 +02:00
|
|
|
result.HTML = byteutil.B2S(htmlBytes.Bytes())
|
2023-09-29 10:39:56 +02:00
|
|
|
result.HTML = SanitizeToHTML(result.HTML)
|
|
|
|
result.HTML = MinifyHTML(result.HTML)
|
|
|
|
|
|
|
|
return result
|
2023-05-09 12:16:10 +02:00
|
|
|
}
|