func sanatizeCaptions(caption string) string {
// captions may contain spurious <p> and \n's, which lead
// to pdflatex fails because of line breaks. Hence, we remove them.
caption = strings.Replace(caption, "\n", " ", -1)
// captions may contain spurious <p> and \n's, which lead
// to pdflatex fails because of line breaks. Hence, we remove them.
caption = strdel.RegExp(caption, `Figure \d+: `)
caption = strdel.RegExp(caption, `Fig. \d+: `)
//Debug("total : |%q|\n", total)
return caption
}
func sanatizeExtractedAuthor(a string) string {
a = removeDateFromAuthor(a)
// remove by-words
a = strdel.RegExp(a, "[Bb]y")
a = strdel.Word(a, "on")
a = strdel.Word(a, "at")
a = strdel.RegExp(a, "[Pp]osted")
a = strdel.RegExp(a, "[Ee]ditor")
a = strdel.RegExp(a, "Guest Contributor")
// remove Twitter
a = strdel.RegExp(a, `Follow|@[[:alpha:]]+|([a-zA-Z]+)Twitter`)
// Remove punctation
a = strings.Replace(a, ".", "", -1)
return strings.TrimSpace(a)
}
// removeNonRegChars deletes any number of non-regular chars, except for _-
// from string s
func removeNonRegChars(s string) string {
return strdel.RegExp(s, "[^A-Za-z0-9_\\- ]+")
}