Пример #1
0
  private void Parse_capt(Gfh_tag_rdr tag_rdr, Gfh_tag anch_head) {
    this.capt_bgn = anch_head.Src_end(); // capt starts after <a>
    Gfh_tag anch_tail = tag_rdr.Tag__move_fwd_tail(Gfh_tag_.Id__a); // </a>
    this.capt_end = anch_tail.Src_bgn(); // get capt between "<a>" and "</a>
    this.src_end = anch_tail.Src_end();

    // skip ns in href / capt
    if (href_ns_id != Xow_ns_.Tid__main) { // not main; try to remove template name;		
      int capt_bgn_wo_ns = capt_bgn + href_ns_name_len;
      href_bgn +=
          href_ns_name_len; // skip ns_name for href; EX: "Help:A" -> "A"; "Help" will be saved as
      // encoded number
      if (Bry_.Match(
          capt_src,
          capt_bgn,
          capt_bgn_wo_ns,
          href_ns_name)) { // capt matches ns_name; EX: <a href='/wiki/Help:A'>Help:A</a> ->
        // "Help:A" matches "Help:"
        capt_bgn = capt_bgn_wo_ns; // skip ns; "Help:"
        capt_has_ns = true;
      }
    }

    // get text splits
    this.text_tid =
        href_itm.Tid() == Xoh_anch_href_data.Tid__anch
            ? Xoh_anch_capt_itm.Tid__diff
            : capt_itm.Parse(
                rdr, capt_has_ns, href_src, href_bgn, href_end, src, capt_bgn, capt_end);
    int split_pos = capt_itm.Split_pos();
    this.text_0_src = href_src;
    this.text_0_bgn = href_bgn;
    this.text_0_end = href_end;
    this.text_1_src = capt_src;
    this.text_1_bgn = capt_bgn;
    this.text_1_end = capt_end;
    switch (text_tid) {
      case Xoh_anch_capt_itm.Tid__same:
        // case Xoh_anch_capt_itm.Tid__href_pipe:
      case Xoh_anch_capt_itm.Tid__diff: // nothing to do; href / capt already set above
        break;
      case Xoh_anch_capt_itm.Tid__more:
        this.text_1_bgn = split_pos;
        break;
      case Xoh_anch_capt_itm.Tid__less:
        this.text_0_end = split_pos;
        this.text_1_src = href_src;
        this.text_1_bgn = split_pos;
        this.text_1_end = href_end;
        break;
    }
  }
Пример #2
0
 public boolean Parse1(
     Xoh_hdoc_wkr hdoc_wkr,
     Xoh_hdoc_ctx hctx,
     Gfh_tag_rdr tag_rdr,
     byte[] src,
     Gfh_tag anch_head) {
   Init(src);
   this.src_bgn = anch_head.Src_bgn();
   rdr.Init_by_wkr(tag_rdr.Err_wkr(), "lnki", src_bgn, src.length);
   Gfh_atr title_atr = anch_head.Atrs__get_by_or_empty(Gfh_atr_.Bry__title);
   Parse_href(hctx, anch_head);
   Parse_cls(anch_head);
   Parse_capt(tag_rdr, anch_head);
   Parse_title(title_atr);
   hdoc_wkr.On_lnki(this);
   return true;
 }
Пример #3
0
 private void Parse_cls(Gfh_tag anch_head) {
   byte[] cls_bry = anch_head.Atrs__get_as_bry(Gfh_atr_.Bry__class);
   if (Bry_.Len_eq_0(cls_bry)) return;
   this.cls_tid =
       Xoh_anch_cls_.Trie.Match_byte_or(cls_bry, 0, cls_bry.length, Xoh_anch_cls_.Tid__unknown);
 }