opencode/picoclaw
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

perf: pre-compile regexes at package level

Browse source 
Move regexp.MustCompile calls from inside methods to package-level
variables in web.go (7 regexes) and loader.go (2 regexes).
This avoids repeated compilation on every invocation.

Amp-Thread-ID: https://ampcode.com/threads/T-019c79c3-ea1c-7471-b09d-be90ba0e1ca0
Co-authored-by: Amp <amp@ampcode.com>
This commit is contained in:
Yasuhiro Matsumoto 2026-02-20 16:03:35 +09:00
parent e599573ed4
commit 57c9bd03d3
2 changed files with 28 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
pkg/skills/loader.go
View file

@ -13,7 +13,11 @@ import (
"github.com/sipeed/picoclaw/pkg/logger"
)
var namePattern = regexp.MustCompile(`^[a-zA-Z0-9]+(-[a-zA-Z0-9]+)*$`)
var (
namePattern = regexp.MustCompile(`^[a-zA-Z0-9]+(-[a-zA-Z0-9]+)*$`)
reFrontmatter = regexp.MustCompile(`(?s)^---(?:\r\n|\n|\r)(.*?)(?:\r\n|\n|\r)---`)
reStripFrontmatter = regexp.MustCompile(`(?s)^---(?:\r\n|\n|\r)(.*?)(?:\r\n|\n|\r)---(?:\r\n|\n|\r)*`)
)
const (
MaxNameLength = 64
@ -318,11 +322,7 @@ func (sl *SkillsLoader) parseSimpleYAML(content string) map[string]string {
}
func (sl *SkillsLoader) extractFrontmatter(content string) string {
// Support \n (Unix), \r\n (Windows), and \r (classic Mac) line endings for frontmatter blocks
// (?s) enables DOTALL so . matches newlines;
// ^--- at start, then ... --- at start of line, honoring all three line ending types
re := regexp.MustCompile(`(?s)^---(?:\r\n|\n|\r)(.*?)(?:\r\n|\n|\r)---`)
match := re.FindStringSubmatch(content)
match := reFrontmatter.FindStringSubmatch(content)
if len(match) > 1 {
return match[1]
}
@ -330,12 +330,7 @@ func (sl *SkillsLoader) extractFrontmatter(content string) string {
}
func (sl *SkillsLoader) stripFrontmatter(content string) string {
// Support \n (Unix), \r\n (Windows), and \r (classic Mac) line endings for frontmatter blocks
// (?s) enables DOTALL so . matches newlines;
// ^--- at start, then ... --- at start of line, honoring all three line ending types
// Match zero or more trailing line endings after closing --- (handles both with and without blank lines)
re := regexp.MustCompile(`(?s)^---(?:\r\n|\n|\r)(.*?)(?:\r\n|\n|\r)---(?:\r\n|\n|\r)*`)
return re.ReplaceAllString(content, "")
return reStripFrontmatter.ReplaceAllString(content, "")
}
func escapeXML(s string) string {

37
pkg/tools/web.go
View file

@ -16,6 +16,19 @@ const (
userAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
)
// Pre-compiled regexes for HTML text extraction
var (
reScript = regexp.MustCompile(`<script[\s\S]*?</script>`)
reStyle = regexp.MustCompile(`<style[\s\S]*?</style>`)
reTags = regexp.MustCompile(`<[^>]+>`)
reWhitespace = regexp.MustCompile(`[^\S\n]+`)
reBlankLines = regexp.MustCompile(`\n{3,}`)
// DuckDuckGo result extraction
reDDGLink = regexp.MustCompile(`<a[^>]*class="[^"]*result__a[^"]*"[^>]*href="([^"]+)"[^>]*>([\s\S]*?)</a>`)
reDDGSnippet = regexp.MustCompile(`<a class="result__snippet[^"]*".*?>([\s\S]*?)</a>`)
)
type SearchProvider interface {
Search(ctx context.Context, query string, count int) (string, error)
}
@ -118,8 +131,7 @@ func (p *DuckDuckGoSearchProvider) extractResults(html string, count int, query
// Try finding the result links directly first, as they are the most critical
// Pattern: <a class="result__a" href="...">Title</a>
// The previous regex was a bit strict. Let's make it more flexible for attributes order/content
reLink := regexp.MustCompile(`<a[^>]*class="[^"]*result__a[^"]*"[^>]*href="([^"]+)"[^>]*>([\s\S]*?)</a>`)
matches := reLink.FindAllStringSubmatch(html, count+5)
matches := reDDGLink.FindAllStringSubmatch(html, count+5)
if len(matches) == 0 {
return fmt.Sprintf("No results found or extraction failed. Query: %s", query), nil
@ -136,8 +148,7 @@ func (p *DuckDuckGoSearchProvider) extractResults(html string, count int, query
// A better regex approach: iterate through text and find matches in order
// But for now, let's grab all snippets too
reSnippet := regexp.MustCompile(`<a class="result__snippet[^"]*".*?>([\s\S]*?)</a>`)
snippetMatches := reSnippet.FindAllStringSubmatch(html, count+5)
snippetMatches := reDDGSnippet.FindAllStringSubmatch(html, count+5)
maxItems := min(len(matches), count)
@ -172,8 +183,7 @@ func (p *DuckDuckGoSearchProvider) extractResults(html string, count int, query
}
func stripTags(content string) string {
re := regexp.MustCompile(`<[^>]+>`)
return re.ReplaceAllString(content, "")
return reTags.ReplaceAllString(content, "")
}
type PerplexitySearchProvider struct {
@ -483,19 +493,14 @@ func (t *WebFetchTool) Execute(ctx context.Context, args map[string]interface{})
}
func (t *WebFetchTool) extractText(htmlContent string) string {
re := regexp.MustCompile(`<script[\s\S]*?</script>`)
result := re.ReplaceAllLiteralString(htmlContent, "")
re = regexp.MustCompile(`<style[\s\S]*?</style>`)
result = re.ReplaceAllLiteralString(result, "")
re = regexp.MustCompile(`<[^>]+>`)
result = re.ReplaceAllLiteralString(result, "")
result := reScript.ReplaceAllLiteralString(htmlContent, "")
result = reStyle.ReplaceAllLiteralString(result, "")
result = reTags.ReplaceAllLiteralString(result, "")
result = strings.TrimSpace(result)
re = regexp.MustCompile(`[^\S\n]+`)
result = re.ReplaceAllString(result, " ")
re = regexp.MustCompile(`\n{3,}`)
result = re.ReplaceAllString(result, "\n\n")
result = reWhitespace.ReplaceAllString(result, " ")
result = reBlankLines.ReplaceAllString(result, "\n\n")
lines := strings.Split(result, "\n")
var cleanLines []string