Removed some TODO items

https://github.com/pemistahl/lingua-go/discussions/50

README.md

@@ -421,15 +421,15 @@ A document with content "This is a test" when searched with the phrase
 "this test" therefore gets a score of 8: the entire phrase does not
 match but each word gets four points.
 
-Trigrams are sometimes strange: In a text containing the words
-"software" and "#socialmedia", a search for "#software" returns a
-result because the trigram "#so" is part of "#socialmedia".
+Trigrams are sometimes strange: In a text containing the words "main"
+and "rail", a search for "mail" returns a match because the trigrams
+"mai" and "ail" are found. In this situation, the result has a score
+of 0.
 
 ## Limitations
 
 Page titles are filenames with `.md` appended. If your filesystem
-cannot handle it, it can't be a page title. Specifically, *no slashes*
-in filenames.
+cannot handle it, it can't be a page name.
 
 The pages are indexed as the server starts and the index is kept in
 memory. If you have a ton of pages, this surely wastes a lot of

TODO.md

@@ -9,15 +9,7 @@ Post by Delta Chat? That is, allow certain encrypted emails to post.
 
 Convert the existing wiki.
 
-Investigate how to run a multi-lingual wiki where an appropriate
-template is used based on the language of the page. This is important
-because the template needs to use the appropriate `lang` attribute for
-hyphenation to work.
-
 Investigate how to run a multi-linugual wiki where an appropriate
 version of a page is served based on language preferences of the user.
 This is a low priority issue since it's probably only of interest for
 corporate or governmental sites.
-
-Switch from trigram search to a simple full text search engine?
-https://artem.krylysov.com/blog/2020/07/28/lets-build-a-full-text-search-engine/

page.go

@@ -105,7 +105,7 @@ func (p *Page) handleTitle(replace bool) {
 func (p *Page) renderHtml() {
 	maybeUnsafeHTML := markdown.ToHTML(p.Body, nil, nil)
 	p.Html = sanitizeBytes(maybeUnsafeHTML)
-	p.Language = p.language(p.plainText())
+	p.Language = language(p.plainText())
 }
 
 // plainText renders the Page.Body to plain text and returns it,
@@ -141,17 +141,12 @@ func (p *Page) summarize(q string) {
 	p.Score = score(q, string(p.Body)) + score(q, p.Title)
 	t := p.plainText()
 	p.Html = sanitize(snippets(q, t))
-	p.Language = p.language(t)
+	p.Language = language(t)
 }
 
-func (p *Page) language (s string) string {
+func language(s string) string {
 	if language, ok := detector.DetectLanguageOf(s); ok {
-		switch language {
-		case lingua.English:
-			return "en"
-		case lingua.German:
-			return "de"
-		}
+		return strings.ToLower(language.IsoCode639_1().String())
 	}
 	return ""
 }

page_test.go

@@ -76,3 +76,14 @@ Moonlight floods the aisle`)}
 		_ = os.RemoveAll("testdata")
 	})
 }
+
+func TestLanguage(t *testing.T) {
+	l := language(`
+My back hurts at night
+My shoulders won't budge today
+Winter bones I say`)
+	if l != "en" {
+		t.Logf("Language detected: %s", l)
+		t.Fail()
+	}
+}