diff options
Diffstat (limited to 'lib/hocr')
| -rw-r--r-- | lib/hocr/hocr.go | 24 | ||||
| -rw-r--r-- | lib/hocr/lines.go | 12 |
2 files changed, 18 insertions, 18 deletions
diff --git a/lib/hocr/hocr.go b/lib/hocr/hocr.go index 0d10819..bbcf8a2 100644 --- a/lib/hocr/hocr.go +++ b/lib/hocr/hocr.go @@ -12,27 +12,27 @@ type Hocr struct { } type OcrLine struct { - Class string `xml:"class,attr"` - Id string `xml:"id,attr"` - Title string `xml:"title,attr"` + Class string `xml:"class,attr"` + Id string `xml:"id,attr"` + Title string `xml:"title,attr"` Words []OcrWord `xml:"span"` - Text string `xml:",chardata"` + Text string `xml:",chardata"` } type OcrWord struct { - Class string `xml:"class,attr"` - Id string `xml:"id,attr"` - Title string `xml:"title,attr"` + Class string `xml:"class,attr"` + Id string `xml:"id,attr"` + Title string `xml:"title,attr"` Chars []OcrChar `xml:"span"` - Text string `xml:",chardata"` + Text string `xml:",chardata"` } type OcrChar struct { - Class string `xml:"class,attr"` - Id string `xml:"id,attr"` - Title string `xml:"title,attr"` + Class string `xml:"class,attr"` + Id string `xml:"id,attr"` + Title string `xml:"title,attr"` Chars []OcrChar `xml:"span"` - Text string `xml:",chardata"` + Text string `xml:",chardata"` } // Returns the confidence for a word based on its x_wconf value diff --git a/lib/hocr/lines.go b/lib/hocr/lines.go index 84c2130..00acd1f 100644 --- a/lib/hocr/lines.go +++ b/lib/hocr/lines.go @@ -36,27 +36,27 @@ func parseLineDetails(h Hocr, i image.Image, name string) (line.Details, error) var ln line.Detail ln.Name = l.Id - ln.Avgconf = (totalconf/float64(num)) / 100 + ln.Avgconf = (totalconf / float64(num)) / 100 linetext := "" linetext = l.Text - if(noText(linetext)) { + if noText(linetext) { linetext = "" for _, w := range l.Words { - if(w.Class != "ocrx_word") { + if w.Class != "ocrx_word" { continue } linetext += w.Text + " " } } - if(noText(linetext)) { + if noText(linetext) { linetext = "" for _, w := range l.Words { - if(w.Class != "ocrx_word") { + if w.Class != "ocrx_word" { continue } for _, c := range w.Chars { - if(c.Class != "ocrx_cinfo") { + if c.Class != "ocrx_cinfo" { continue } linetext += c.Text |