// Puttting it all together
func Dedup(oURL *url.URL,
least3Files []repo.FullArticle, lg loghttp.FuncBufUniv, fs fsi.FileSystem) *html.Node {
opts := domclean2.CleaningOptions{Proxify: true, Beautify: true}
// opts.FNamer = fNamer
opts.AddOutline = true
// opts.RemoteHost = fetch.HostFromStringUrl(least3Files[0].Url)
opts.RemoteHost = oURL.Host
//
// domclean
for i := 0; i < len(least3Files); i++ {
fNamer := domclean2.FileNamer(logDir, i)
fNamer() // first call yields key
lg("cleaning %4.1fkB from %v", float64(len(least3Files[i].Body))/1024,
stringspb.ToLenR(least3Files[i].Url, 60))
doc, err := domclean2.DomClean(least3Files[i].Body, opts)
lg(err)
fileDump(lg, fs, doc, fNamer, ".html")
}
if false {
//
// Textify with brute force
for i := 0; i < len(least3Files); i++ {
fNamer := domclean2.FileNamer(logDir, i)
fNamer() // first call yields key
bts, err := fs.ReadFile(fNamer() + ".html")
lg(err)
doc, err := html.Parse(bytes.NewReader(bts))
lg(err)
textifyBruteForce(doc)
var buf bytes.Buffer
err = html.Render(&buf, doc)
lg(err)
b := buf.Bytes()
b = bytes.Replace(b, []byte("[br]"), []byte("\n"), -1)
fileDump(lg, fs, b, fNamer, "_raw.txt")
}
}
//
// Textify with more finetuning.
// Save result to memory.
textsByArticOutl := map[string][]*TextifiedTree{}
for i := 0; i < len(least3Files); i++ {
fNamer := domclean2.FileNamer(logDir, i)
fnKey := fNamer() // first call yields key
bts, err := fs.ReadFile(fNamer() + ".html")
doc, err := html.Parse(bytes.NewReader(bts))
lg(err)
fNamer() // one more
//
mp, bts := BubbledUpTextExtraction(doc, fnKey)
fileDump(lg, fs, bts, fNamer, ".txt")
mpSorted, dump := orderByOutline(mp)
fileDump(lg, fs, dump, fNamer, ".txt")
textsByArticOutl[fnKey] = mpSorted
// for k, v := range mpSorted {
// if k%33 != 0 {
// continue
// }
// log.Printf("%3v: %v %14v %v\n", k, v.SourceID, v.Outline, v.Lvl)
// }
}
//
//
// We progress from level 1 downwards.
// Lower levels skip weeded out higher levels,
// to save expensive levenshtein comparisons
var skipPrefixes = map[string]bool{}
for weedStage := 1; weedStage <= stageMax; weedStage++ {
fNamer := domclean2.FileNamer(logDir, 0)
fnKey := fNamer() // first call yields key
levelsToProcess = map[int]bool{weedStage: true}
frags := similarTextifiedTrees(textsByArticOutl, skipPrefixes, map[string]bool{fnKey: true})
similaritiesToFile(fs, logDir, frags, weedStage)
for _, frag := range frags {
if len(frag.Similars) >= numTotal-1 &&
frag.SumRelLevenshtein/(numTotal-1) < 0.2 {
skipPrefixes[frag.Outline+"."] = true
}
}
b := new(bytes.Buffer)
for k, _ := range skipPrefixes {
b.WriteString(k)
b.WriteByte(32)
}
// log.Printf("%v\n", b.String())
}
//
// Apply dedup
fNamer := domclean2.FileNamer(logDir, 0)
fNamer() // first call yields key
bts, err := fs.ReadFile(fNamer() + ".html")
lg(err)
doc, err := html.Parse(bytes.NewReader(bts))
lg(err)
dedupApply(doc, skipPrefixes)
// A special after dedup cleaning:
// Remove ol and cfrm attributes
var fr func(*html.Node)
fr = func(n *html.Node) {
if n.Type == html.ElementNode {
attr2 := make([]html.Attribute, 0, len(n.Attr))
for _, attr := range n.Attr {
if attr.Key != "ol" && attr.Key != "cfrm" {
attr2 = append(attr2, attr)
}
}
n.Attr = attr2
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
fr(c)
}
}
fr(doc)
if false {
// does not add value
var b7 bytes.Buffer
err := html.Render(&b7, doc)
lg(err)
doc, err = domclean2.DomClean(b7.Bytes(), opts)
lg(err)
} else {
domclean2.DomFormat(doc)
}
return doc
}
// handleFetchURL either displays a form for requesting an url
// or it returns the URL´s contents.
func handleFetchURL(w http.ResponseWriter, r *http.Request, m map[string]interface{}) {
lg, b := loghttp.BuffLoggerUniversal(w, r)
_ = b
// on live server => always use https
if r.URL.Scheme != "https" && !util_appengine.IsLocalEnviron() {
r.URL.Scheme = "https"
r.URL.Host = r.Host
lg("lo - redirect %v", r.URL.String())
http.Redirect(w, r, r.URL.String(), http.StatusFound)
}
/*
To distinguish between posted and getted value,
we check the "post-only" slice of values first.
If nothing's there, but FormValue *has* a value,
then it was "getted", otherwise "posted"
*/
rURL := ""
urlAs := ""
err := r.ParseForm()
lg(err)
if r.PostFormValue(routes.URLParamKey) != "" {
urlAs += "url posted "
rURL = r.PostFormValue(routes.URLParamKey)
}
if r.FormValue(routes.URLParamKey) != "" {
if rURL == "" {
urlAs += "url getted "
rURL = r.FormValue(routes.URLParamKey)
}
}
// lg("received %v: %q", urlAs, rURL)
if len(rURL) == 0 {
tplAdder, tplExec := tplx.FuncTplBuilder(w, r)
tplAdder("n_html_title", "Fetch some http data", nil)
m := map[string]string{
"protocol": "https",
"host": r.Host, // not fetch.HostFromReq(r)
"path": routes.ProxifyURI,
"name": routes.URLParamKey,
"val": "google.com",
}
if util_appengine.IsLocalEnviron() {
m["protocol"] = "http"
}
tplAdder("n_cont_0", c_formFetchUrl, m)
tplExec(w, r)
} else {
r.Header.Set("X-Custom-Header-Counter", "nocounter")
bts, inf, err := fetch.UrlGetter(r, fetch.Options{URL: rURL})
lg(err)
tp := mime.TypeByExtension(path.Ext(inf.URL.Path))
if false {
ext := path.Ext(rURL)
ext = strings.ToLower(ext)
tp = mime.TypeByExtension(ext)
}
w.Header().Set("Content-Type", tp)
// w.Header().Set("Content-type", "text/html; charset=latin-1")
if r.FormValue("dbg") != "" {
w.Header().Set("Content-type", "text/html; charset=utf-8")
fmt.Fprintf(w, "%s<br>\n %s<br>\n %v", inf.URL.Path, tp, inf.URL.String())
return
}
opts := domclean2.CleaningOptions{Proxify: true}
opts.Beautify = true // "<a> Linktext without trailing space"
opts.RemoteHost = fetch.HostFromStringUrl(rURL)
// opts.ProxyHost = routes.AppHost()
opts.ProxyHost = fetch.HostFromReq(r)
if !util_appengine.IsLocalEnviron() {
opts.ProxyHost = fetch.HostFromReq(r)
}
doc, err := domclean2.DomClean(bts, opts)
var bufRend bytes.Buffer
err = html.Render(&bufRend, doc)
lg(err)
w.Write(bufRend.Bytes())
}
}