mirror of
https://github.com/go-gitea/gitea.git
synced 2026-10-30 19:14:03 +00:00
1ebeade2c1
Code search now matches case-insensitive literal substrings like GitHub, in every script. Word tokenizers can't do this: the ES pattern dropped every non-ASCII word, and the `standard` tokenizer keeps `console.log` as one token. - Elasticsearch indexes positional trigrams, plus 1-2 grams for short terms - Bleve indexes distinct 1-3 grams as a candidate filter and verifies candidates against the content before paging, because phrase queries over trigrams are quadratic in repeated grams - Snippet offsets come from the original content, so `<em>` in sources and width-changing lowercase no longer misplace them - `search_mode=fuzzy` requests behave like Words, the UI never offered fuzzy for code search - The ES code indexer test now runs in CI, it was skipped before There are no UI changes. Both code indexes rebuild after upgrade. Fixes: https://github.com/go-gitea/gitea/issues/40027 Fixes: https://github.com/go-gitea/gitea/issues/16158 Fixes: https://github.com/go-gitea/gitea/issues/21359 --------- Co-authored-by: silverwind <me@silverwind.io> Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
92 lines
2.2 KiB
Go
92 lines
2.2 KiB
Go
// Copyright 2023 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package internal
|
|
|
|
import (
|
|
"strings"
|
|
"unicode"
|
|
"unicode/utf8"
|
|
|
|
"gitea.dev/modules/indexer"
|
|
"gitea.dev/modules/indexer/internal"
|
|
"gitea.dev/modules/log"
|
|
)
|
|
|
|
const filenameMatchNumberOfLines = 7 // Copied from GitHub search
|
|
|
|
func FilenameIndexerID(repoID int64, filename string) string {
|
|
return internal.Base36(repoID) + "_" + filename
|
|
}
|
|
|
|
func ParseIndexerID(indexerID string) (int64, string) {
|
|
before, after, ok := strings.Cut(indexerID, "_")
|
|
if !ok {
|
|
log.Error("Unexpected ID in repo indexer: %s", indexerID)
|
|
}
|
|
repoID, _ := internal.ParseBase36(before)
|
|
return repoID, after
|
|
}
|
|
|
|
func FilenameOfIndexerID(indexerID string) string {
|
|
_, after, ok := strings.Cut(indexerID, "_")
|
|
if !ok {
|
|
log.Error("Unexpected ID in repo indexer: %s", indexerID)
|
|
}
|
|
return after
|
|
}
|
|
|
|
// FilenameMatchIndexPos returns the boundaries of its first seven lines.
|
|
func FilenameMatchIndexPos(content string) (int, int) {
|
|
count := 1
|
|
for i, c := range content {
|
|
if c == '\n' {
|
|
count++
|
|
if count == filenameMatchNumberOfLines {
|
|
return 0, i
|
|
}
|
|
}
|
|
}
|
|
return 0, len(content)
|
|
}
|
|
|
|
func SearchTerms(opts *SearchOptions) []string {
|
|
if opts.Keyword == "" {
|
|
return nil
|
|
}
|
|
if opts.SearchMode == "" || opts.SearchMode == indexer.SearchModeExact {
|
|
return []string{opts.Keyword}
|
|
} else {
|
|
return strings.Fields(opts.Keyword)
|
|
}
|
|
}
|
|
|
|
// ContentMatchIndexPos returns the byte range of the earliest term in content, or -1, -1 unless all terms occur
|
|
func ContentMatchIndexPos(content string, terms []string) (int, int) {
|
|
lowerContent := strings.ToLower(content)
|
|
start, end := -1, -1
|
|
for _, term := range terms {
|
|
lowerTerm := strings.ToLower(term)
|
|
position := strings.Index(lowerContent, lowerTerm)
|
|
if position < 0 {
|
|
return -1, -1
|
|
}
|
|
if start < 0 || position < start {
|
|
start, end = position, position+len(lowerTerm)
|
|
}
|
|
}
|
|
lowerOffset, originalStart := 0, -1
|
|
for offset := 0; offset < len(content); {
|
|
character, size := utf8.DecodeRuneInString(content[offset:])
|
|
if lowerOffset == start {
|
|
originalStart = offset
|
|
}
|
|
lowerOffset += utf8.RuneLen(unicode.ToLower(character))
|
|
offset += size
|
|
if lowerOffset == end {
|
|
return originalStart, offset
|
|
}
|
|
}
|
|
return -1, -1
|
|
}
|