1
0
mirror of https://github.com/gnosygnu/xowa.git synced 2024-09-28 22:40:50 +00:00

HTML Databases: Fix loading of plain-text pages; Normalize some behavior in page-sync code [#320]

This commit is contained in:
gnosygnu 2019-01-05 11:47:24 -05:00
parent 9e5a13f54f
commit 2b4320b302
22 changed files with 158 additions and 82 deletions

View File

@ -91,9 +91,7 @@ public class Xosync_read_mgr implements Gfo_invk {
// auto-sync page
Xoa_app app = wiki.App();
Xoh_page hpg = new Xoh_page();
update_mgr.Init_by_app(app);
update_mgr.Init_by_page(wiki, hpg);
Xowm_parse_data parse_data = update_mgr.Update(app.Wmf_mgr().Download_wkr(), wiki, page_ttl);
if (parse_data == null)
return rv;

View File

@ -35,10 +35,6 @@ public class Xosync_update_mgr {
public void Init_by_app(Xoa_app app) {
hctx.Init_by_app(app);
}
public void Init_by_page(Xow_wiki wiki, Xoa_page page) {
hctx.Init_by_page(wiki, page);
page.Hdump_mgr().Clear();
}
public Xowm_parse_data Update(Xof_download_wkr download_wkr, Xow_wiki wiki, Xoa_ttl page_ttl) {
Xoh_page hpg = (Xoh_page)hctx.Page();
@ -97,6 +93,7 @@ public class Xosync_update_mgr {
// init_by_page for bldr, parser, hdoc
hctx.Init_by_page(wiki, hpg);
hpg.Hdump_mgr().Clear();
hdoc_bldr.Init_by_page(bfr, hpg, hctx, src, 0, src_len);
hdoc_parser_wkr.Init_by_page(hctx, src, 0, src_len);

View File

@ -53,7 +53,7 @@ public class Xosync_page_loader {
byte[] img_src_val = img_src_atr.Val();
byte path_tid = Xosync_img_src_parser.Src_xo_trie.Match_byte_or(trv, img_src_val, Xosync_img_src_parser.Path__unknown);
switch (path_tid) {
case Xosync_img_src_parser.Path__file:
case Xosync_img_src_parser.Path__file_wm:
Add_img(wiki, hpg, img_tag, img_src_atr, img_src_val, path_tid, Xosync_img_src_parser.Bry__xowa_file, wiki.App().Fsys_mgr().File_dir().To_http_file_bry());
break;
case Xosync_img_src_parser.Path__math:
@ -74,7 +74,7 @@ public class Xosync_page_loader {
img_src_val = Bry_.Replace(img_src_val, src_find, src_repl);
// parse src
img_src_parser.Parse(err_wkr, hctx, wiki.Domain_bry(), img_src_atr.Val_bgn(), img_src_atr.Val_end());
img_src_parser.Parse(err_wkr, hctx, wiki.Domain_bry(), img_src_atr.Src(), img_src_atr.Val_bgn(), img_src_atr.Val_end());
if (img_src_parser.File_ttl_bry() == null) return null; // skip images that don't follow format of "commons.wikimedia.org/thumb/7/70/A.png"; for example, enlarge buttons
// create img

View File

@ -17,7 +17,9 @@ package gplx.xowa.addons.wikis.pages.syncs.core.parsers; import gplx.*; import g
import org.junit.*;
import gplx.langs.htmls.*;
public class Xosync_hdoc_parser__err__tst {
@Before public void init() {fxt.Clear();} private final Xosync_hdoc_parser__fxt fxt = new Xosync_hdoc_parser__fxt();
private final Xosync_hdoc_parser__fxt fxt = new Xosync_hdoc_parser__fxt();
@Before public void init() {fxt.Init(false);}
@After public void term() {fxt.Term();}
@Test public void Url_does_not_start_with_upload_wikimedia_org() {
fxt.Exec__parse(Gfh_utl.Replace_apos("<img src='//fail/wikipedia/commons/thumb/7/70/A.png/220px-A.png'>"))
.Test__html(Gfh_utl.Replace_apos("<!--wm.parse:img src does not start with known sequence--><img src='//fail/wikipedia/commons/thumb/7/70/A.png/220px-A.png'>"));

View File

@ -17,7 +17,9 @@ package gplx.xowa.addons.wikis.pages.syncs.core.parsers; import gplx.*; import g
import org.junit.*;
import gplx.langs.htmls.*;
public class Xosync_hdoc_parser__file__tst {
@Before public void init() {fxt.Clear();} private final Xosync_hdoc_parser__fxt fxt = new Xosync_hdoc_parser__fxt();
private final Xosync_hdoc_parser__fxt fxt = new Xosync_hdoc_parser__fxt();
@Before public void init() {fxt.Init(true);}
@After public void term() {fxt.Term();}
@Test public void Commons__thumb() {
fxt.Exec__parse(Gfh_utl.Replace_apos("<img src='//upload.wikimedia.org/wikipedia/commons/thumb/7/70/A.png/320px-A.png'>"))
.Test__html(Gfh_utl.Replace_apos("<img src='xowa:/file/commons.wikimedia.org/thumb/7/0/1/c/A.png/320px.png'>"))
@ -53,4 +55,9 @@ public class Xosync_hdoc_parser__file__tst {
.Test__html(Gfh_utl.Replace_apos("<img src='xowa:/file/commons.wikimedia.org/thumb/7/6/9/a/A.djvu/320px-1.jpg'>"))
.Test__fsdb(fxt.Make__fsdb(Bool_.Y, Bool_.N, "A.djvu", 320, -1, 1));
}
@Test public void Xo() {
fxt.Exec__parse(Gfh_utl.Replace_apos("<img src='file:///mem/xowa/file/commons.wikimedia.org/thumb/7/0/1/c/A.png/320px.png'>"))
.Test__html(Gfh_utl.Replace_apos("<img src='xowa:/file/commons.wikimedia.org/thumb/7/0/1/c/A.png/320px.png'>"))
.Test__fsdb(fxt.Make__fsdb(Bool_.Y, Bool_.N, "A.png", 320, -1, -1));
}
}

View File

@ -22,12 +22,16 @@ public class Xosync_hdoc_parser__fxt {
private final Bry_bfr tmp_bfr = Bry_bfr_.New();
private final Xoh_page hpg = new Xoh_page();
private Xowe_wiki wiki;
public void Clear() {
public void Init(boolean print_errors) {
if (print_errors)
Gfo_usr_dlg_.Instance = Gfo_usr_dlg_.Test_console();
Xoae_app app = Xoa_app_fxt.Make__app__edit();
this.wiki = Xoa_app_fxt.Make__wiki__edit(app);
Xoa_app_fxt.repo2_(app, wiki);
mgr.Init_by_app(app);
mgr.Init_by_page(wiki, hpg);
}
public void Term() {
Gfo_usr_dlg_.Instance = Gfo_usr_dlg_.Noop;
}
public Xosync_hdoc_parser__fxt Exec__parse(String raw) {
mgr.Parse(hpg, wiki, Bry_.Empty, Bry_.new_u8(raw));

View File

@ -17,7 +17,9 @@ package gplx.xowa.addons.wikis.pages.syncs.core.parsers; import gplx.*; import g
import org.junit.*;
import gplx.langs.htmls.*;
public class Xosync_hdoc_parser__misc__tst {
@Before public void init() {fxt.Clear();} private final Xosync_hdoc_parser__fxt fxt = new Xosync_hdoc_parser__fxt();
private final Xosync_hdoc_parser__fxt fxt = new Xosync_hdoc_parser__fxt();
@Before public void init() {fxt.Init(true);}
@After public void term() {fxt.Term();}
@Test public void Math() {
fxt.Exec__parse(Gfh_utl.Replace_apos("<img src='https://wikimedia.org/api/rest_v1/media/math/render/svg/596f8baf206a81478afd4194b44138715dc1a05c' class='mwe-math-fallback-image-inline' aria-hidden='true' style='vertical-align: -2.005ex; width:16.822ex; height:6.176ex;' alt='R_{H}=a\\left({\\frac {m}{3M}}\\right)^{\\frac {1}{3}}'>"))
.Test__html(Gfh_utl.Replace_apos("<img src='xowa:/math/596f8baf206a81478afd4194b44138715dc1a05c.svg' class='mwe-math-fallback-image-inline' aria-hidden='true' style='vertical-align: -2.005ex; width:16.822ex; height:6.176ex;' alt='R_{H}=a\\left({\\frac {m}{3M}}\\right)^{\\frac {1}{3}}'>"))

View File

@ -17,7 +17,9 @@ package gplx.xowa.addons.wikis.pages.syncs.core.parsers; import gplx.*; import g
import org.junit.*;
import gplx.langs.htmls.*;
public class Xosync_hdoc_parser__tst {
@Before public void init() {fxt.Clear();} private final Xosync_hdoc_parser__fxt fxt = new Xosync_hdoc_parser__fxt();
private final Xosync_hdoc_parser__fxt fxt = new Xosync_hdoc_parser__fxt();
@Before public void init() {fxt.Init(true);}
@After public void term() {fxt.Term();}
@Test public void Remove_edit() {
fxt.Exec__parse(Gfh_utl.Replace_apos_concat_lines
( "<h2><span class='mw-headline' id='Section_1'>Section_1</span>"

View File

@ -16,19 +16,21 @@ Apache License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-APACHE2.txt
package gplx.xowa.addons.wikis.pages.syncs.core.parsers; import gplx.*; import gplx.xowa.*; import gplx.xowa.addons.*; import gplx.xowa.addons.wikis.*; import gplx.xowa.addons.wikis.pages.*; import gplx.xowa.addons.wikis.pages.syncs.*; import gplx.xowa.addons.wikis.pages.syncs.core.*;
import gplx.core.brys.*; import gplx.core.btries.*;
import gplx.xowa.files.*; import gplx.xowa.files.repos.*; import gplx.xowa.files.imgs.*;
import gplx.langs.htmls.*; import gplx.xowa.htmls.core.wkrs.*;
import gplx.langs.htmls.*; import gplx.xowa.htmls.core.wkrs.*; import gplx.xowa.htmls.core.wkrs.imgs.atrs.*;
import gplx.xowa.wikis.domains.*;
public class Xosync_img_src_parser {
private final Bry_rdr rdr = new Bry_rdr().Dflt_dlm_(Byte_ascii.Slash);
private final Xof_url_bldr url_bldr = Xof_url_bldr.new_v2();
private final Bry_bfr tmp_bfr = Bry_bfr_.New();
private final byte[] wiki_abrv_commons;
private final Xoh_img_src_data img_src_parser = new Xoh_img_src_data();
private Xoh_hdoc_ctx hctx;
private byte path_tid;
private byte[] img_src_bgn_local, img_src_bgn_remote;
private byte[] page_url, repo_local;
private byte[] raw;
private int raw_len;
public boolean Repo_is_commons() {return repo_is_commons;} private boolean repo_is_commons;
public byte[] File_ttl_bry() {return file_ttl_bry;} private byte[] file_ttl_bry;
@ -58,33 +60,60 @@ public class Xosync_img_src_parser {
// set raw, raw_len; exit if empty
this.raw = raw;
int raw_len = raw.length;
this.raw_len = raw.length;
if (raw_len == 0) return Fail("empty img_src");
rdr.Init_by_src(raw);
// check "//upload.wikimedia.org/" at bgn
// identify type based on beginning; EX: "//upload.wikimedia.org/" -> WM_FILE
this.path_tid = rdr.Chk_or(path_trie, Path__unknown);
switch (path_tid) {
case Path__file: return Parse_file(raw_len);
case Path__math: return Parse_math(raw_len);
default: return Fail("img src does not start with known sequence");
// "//upload.wikimedia.org/"
case Path__file_wm:
return Parse_file_wm();
// "https://wikimedia.org/api/rest_v1/media/math/render/svg/"
case Path__math:
return Parse_math();
// "file:///"
case Path__file_xo:
return Parse_file_xo();
default:
return Fail("img src does not start with known sequence");
}
}
private boolean Parse_file(int raw_len) {
// get repo: either "wikipedia/commons/" or "wiki_type/wiki_lang/"; EX:"wiktionary/fr"
private boolean Parse_file_xo() {
img_src_parser.Clear();
boolean rv = img_src_parser.Parse(rdr.Err_wkr(), hctx, hctx.Wiki__domain_bry(), raw, 0, raw_len);
if (rv) {
this.repo_is_commons = img_src_parser.Repo_is_commons();
this.file_is_orig = img_src_parser.File_is_orig();
this.file_ttl_bry = img_src_parser.File_ttl_bry();
this.file_ext = Xof_ext_.new_by_ttl_(file_ttl_bry);
if (!file_is_orig) {
this.file_w = img_src_parser.File_w();
if (img_src_parser.File_page_exists())
this.file_page = img_src_parser.File_page();
if (img_src_parser.File_time_exists())
this.file_time = img_src_parser.File_time();
}
Add_img(hctx.Wiki__domain_itm().Abrv_xo());
}
return rv;
}
private boolean Parse_file_wm() {
// set repo: either "wikipedia/commons/" or "wiki_type/wiki_lang/"; EX:"wiktionary/fr"
if (rdr.Is(Bry__repo_remote))
this.repo_is_commons = true;
else {
if (!rdr.Is(repo_local)) return Fail("unknown repo");
}
// get file_is_orig; note omitting "else" b/c default is file_is_orig == false
// set file_is_orig; note omitting "else" b/c default is file_is_orig == false
if (!rdr.Is(Bry__thumb)) file_is_orig = true; // no "/thumb";
// check md5
// check md5 and skip
if (!Check_md5()) return Fail("invalid md5");
// get file_ttl
// set file_ttl
int file_ttl_bgn = rdr.Pos();
int file_ttl_end = rdr.Find_fwd_lr_or(Byte_ascii.Slash, raw_len);
file_ttl_bry = Bry_.Mid(raw, file_ttl_bgn, file_ttl_end);
@ -92,7 +121,6 @@ public class Xosync_img_src_parser {
this.file_ext = Xof_ext_.new_by_ttl_(file_ttl_bry);
if (file_ext.Id_is_ogg()) file_ext = Xof_ext_.new_by_id_(Xof_ext_.Id_ogv);
// if thumb, get file_w, file_time, file_page
if (!file_is_orig) {
// if "page", then file_page exists; EX: // "page1-320px"
@ -110,7 +138,7 @@ public class Xosync_img_src_parser {
if (file_w == -1) return Fail("invalid file_w");
// get time via "-seek%3D"; EX: "320px-seek%3D67-"
int seek_end = rdr.Find_fwd_rr(Bry__seek);
int seek_end = rdr.Find_fwd_rr_or(Bry__seek, Bry_find_.Not_found);
if (seek_end != Bry_find_.Not_found) {
int file_time_bgn = rdr.Pos();
int file_time_end = rdr.Find_fwd_lr(Byte_ascii.Dash);
@ -118,11 +146,11 @@ public class Xosync_img_src_parser {
}
}
// make image
// register image
Add_img(hctx.Wiki__domain_itm().Abrv_xo());
return true;
}
private boolean Parse_math(int raw_len) {
private boolean Parse_math() {
// set file_ttl_bry to rest of src + ".svg"; EX: "https://wikimedia.org/api/rest_v1/media/math/render/svg/596f8baf206a81478afd4194b44138715dc1a05c" -> "596f8baf206a81478afd4194b44138715dc1a05c.svg"
this.file_ttl_bry = Bry_.Add(Bry_.Mid(raw, rdr.Pos(), raw_len), Byte_ascii.Dot_bry, Xof_ext_.Bry_svg);
this.repo_is_commons = true;
@ -139,8 +167,13 @@ public class Xosync_img_src_parser {
}
public byte[] To_bry() {
switch (path_tid) {
case Path__file: To_bfr_file(tmp_bfr); break;
case Path__math: To_bfr_math(tmp_bfr); break;
case Path__file_wm:
case Path__file_xo:
To_bfr_file(tmp_bfr);
break;
case Path__math:
To_bfr_math(tmp_bfr);
break;
}
return tmp_bfr.To_bry_and_clear();
}
@ -169,7 +202,7 @@ public class Xosync_img_src_parser {
}
private boolean Fail(String fmt) {
this.err_msg = "wm.parse:" + fmt;
String msg = String_.Format("", err_msg + "; page={0} raw={1}", page_url, raw);
String msg = String_.Format(err_msg + "; page={0} raw={1}", page_url, raw);
Gfo_usr_dlg_.Instance.Warn_many("", "", msg);
return false;
}
@ -183,6 +216,19 @@ public class Xosync_img_src_parser {
return true;
}
public static final byte Path__unknown = 0, Path__file_wm = 1, Path__math = 2, Path__file_xo = 3;
private final Btrie_slim_mgr path_trie = Btrie_slim_mgr.cs()
.Add_str_byte("//upload.wikimedia.org/", Path__file_wm)
.Add_str_byte("https://wikimedia.org/api/rest_v1/media/math/render/svg/", Path__math)
.Add_str_byte("file:///", Path__file_xo)
;
public static final byte[] Bry__xowa_file = Bry_.new_a7("xowa:/file/"), Bry__xowa_math = Bry_.new_a7("xowa:/math/");
public static Btrie_slim_mgr Src_xo_trie = Btrie_slim_mgr.cs()
.Add_bry_byte(Bry__xowa_file, Path__file_wm)
.Add_bry_byte(Bry__xowa_math, Path__math)
;
private static final byte[]
Bry__repo_remote = Bry_.new_a7("wikipedia/commons/")
, Bry__thumb = Bry_.new_a7("thumb/")
@ -190,17 +236,6 @@ public class Xosync_img_src_parser {
, Bry__seek = Bry_.new_a7("-seek%3D")
, Bry__page = Bry_.new_a7("page")
;
public static final byte Path__unknown = 0, Path__file = 1, Path__math = 2;
private final Btrie_slim_mgr path_trie = Btrie_slim_mgr.cs()
.Add_str_byte("//upload.wikimedia.org/", Path__file)
.Add_str_byte("https://wikimedia.org/api/rest_v1/media/math/render/svg/", Path__math)
;
public static final byte[] Bry__xowa_file = Bry_.new_a7("xowa:/file/"), Bry__xowa_math = Bry_.new_a7("xowa:/math/");
public static Btrie_slim_mgr Src_xo_trie = Btrie_slim_mgr.cs()
.Add_bry_byte(Bry__xowa_file, Path__file)
.Add_bry_byte(Bry__xowa_math, Path__math)
;
private static byte[] To_wmf_repo_or_null(Bry_bfr bfr, Xow_domain_itm domain_itm) {
// add type; EX: "fr.wiktionary.org" -> "wiktionary/"

View File

@ -30,8 +30,6 @@ public class Sync_html_special implements Xow_special_page {
// update
Xosync_update_mgr updater = new Xosync_update_mgr();
updater.Init_by_app(wiki.App());
Xoh_page hpg = new Xoh_page();
updater.Init_by_page(wiki, hpg);
updater.Update(wiki.App().Wmf_mgr().Download_wkr(), wiki, redirect_ttl);
((Xowe_wiki)wiki).Data_mgr().Redirect((Xoae_page)page, redirect_bry); // HACK: should call page.Redirect_trail() below, but need to handle Display_ttl
// page.Redirect_trail().Itms__add__article(redirect_url, redirect_ttl, null);

View File

@ -27,6 +27,9 @@ public class Xow_hdump_mgr {
public Xow_hdump_mgr__save Save_mgr() {return save_mgr;} private Xow_hdump_mgr__save save_mgr;
public Xow_hdump_mgr__load Load_mgr() {return load_mgr;} private Xow_hdump_mgr__load load_mgr;
public Xoh_hzip_mgr Hzip_mgr() {return hzip_mgr;} private final Xoh_hzip_mgr hzip_mgr = new Xoh_hzip_mgr();
public void Init_by_app(Xoae_app app) {
save_mgr.Init_by_app(app);
}
public void Init_by_db(Xow_wiki wiki) {
byte dflt_zip_tid = gplx.core.ios.streams.Io_stream_tid_.Tid__raw;
boolean dflt_hzip_enable = false;
@ -41,7 +44,7 @@ public class Xow_hdump_mgr {
load_mgr.Init_by_wiki(wiki);
}
public void Init_by_db(byte dflt_zip_tid, boolean dflt_hzip_enable, boolean mode_is_b256) {
int dflt_hzip_tid = dflt_hzip_enable ? Xoh_hzip_dict_.Hzip__v1 : Xoh_hzip_dict_.Hzip__none;
int dflt_hzip_tid = dflt_hzip_enable ? Xoh_hzip_dict_.Hzip__v1 : Xoh_hzip_dict_.Hzip__plain;
save_mgr.Init_by_db(dflt_zip_tid, dflt_hzip_tid, Bool_.N);
}
}

View File

@ -16,13 +16,18 @@ Apache License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-APACHE2.txt
package gplx.xowa.htmls.core; import gplx.*; import gplx.xowa.*; import gplx.xowa.htmls.*;
import gplx.xowa.htmls.core.htmls.*; import gplx.xowa.htmls.core.wkrs.*; import gplx.xowa.htmls.core.hzips.*; import gplx.xowa.htmls.heads.*; import gplx.xowa.htmls.core.dbs.*;
import gplx.core.ios.*; import gplx.core.primitives.*; import gplx.xowa.wikis.data.*; import gplx.xowa.wikis.pages.*;
import gplx.xowa.addons.wikis.pages.syncs.core.*;
public class Xow_hdump_mgr__save {
private final Xow_wiki wiki; private final Xoh_hzip_mgr hzip_mgr; private final Io_stream_zip_mgr zip_mgr;
private final Xosync_update_mgr update_mgr = new Xosync_update_mgr();
private final Xoh_page tmp_hpg; private final Xoh_hzip_bfr tmp_bfr = Xoh_hzip_bfr.New_txt(32); private Bool_obj_ref html_db_is_new = Bool_obj_ref.n_();
private int dflt_zip_tid, dflt_hzip_tid;
public Xow_hdump_mgr__save(Xow_wiki wiki, Xoh_hzip_mgr hzip_mgr, Io_stream_zip_mgr zip_mgr, Xoh_page tmp_hpg) {
this.wiki = wiki; this.hzip_mgr = hzip_mgr; this.zip_mgr = zip_mgr; this.tmp_hpg = tmp_hpg;
}
public void Init_by_app(Xoae_app app) {
update_mgr.Init_by_app(app);
}
public void Init_by_db(int dflt_zip_tid, int dflt_hzip_tid, boolean mode_is_b256) {
this.dflt_zip_tid = dflt_zip_tid; this.dflt_hzip_tid = dflt_hzip_tid; tmp_bfr.Mode_is_b256_(mode_is_b256);
}
@ -32,12 +37,12 @@ public class Xow_hdump_mgr__save {
Bld_hdump(page);
tmp_hpg.Ctor_by_hdiff(tmp_bfr, page, page.Wikie().Msg_mgr().Val_by_id(gplx.xowa.langs.msgs.Xol_msg_itm_.Id_toc));
Xow_db_file html_db = Get_html_db(wiki, page, html_db_is_new.Val_n_());
return Save(tmp_hpg, html_db.Tbl__html(), html_db_is_new.Val(), true);
return Save(page, tmp_hpg, html_db.Tbl__html(), html_db_is_new.Val(), true);
}
}
public int Save(Xoh_page hpg, Xowd_html_tbl html_tbl, boolean insert, boolean use_hzip_dflt) {
public int Save(Xoae_page page, Xoh_page hpg, Xowd_html_tbl html_tbl, boolean insert, boolean use_hzip_dflt) {
int hzip_tid = use_hzip_dflt ? dflt_hzip_tid : Xoh_hzip_dict_.Hzip__none;
byte[] db_body = Write(tmp_bfr, wiki, hpg, hzip_mgr, zip_mgr, dflt_zip_tid, hzip_tid, hpg.Db().Html().Html_bry());
byte[] db_body = Write(tmp_bfr, wiki, page, hpg, hzip_mgr, zip_mgr, dflt_zip_tid, hzip_tid, hpg.Db().Html().Html_bry());
if (insert) html_tbl.Insert(hpg, dflt_zip_tid, dflt_hzip_tid, db_body);
else html_tbl.Update(hpg, dflt_zip_tid, dflt_hzip_tid, db_body);
return db_body.length;
@ -47,8 +52,16 @@ public class Xow_hdump_mgr__save {
wiki.Html__wtr_mgr().Wkr(Xopg_page_.Tid_read).Write_body(tmp_bfr, page.Wikie().Parser_mgr().Ctx(), Xoh_wtr_ctx.Hdump, page); // save as hdump_fmt
page.Db().Html().Html_bry_(tmp_bfr.To_bry_and_clear());
}
private byte[] Write(Xoh_hzip_bfr bfr, Xow_wiki wiki, Xoh_page hpg, Xoh_hzip_mgr hzip_mgr, Io_stream_zip_mgr zip_mgr, int zip_tid, int hzip_tid, byte[] src) {
if (hzip_tid != Xoh_hzip_dict_.Hzip__none) src = hzip_mgr.Encode_as_bry((Xoh_hzip_bfr)bfr.Clear(), wiki, hpg, src);
private byte[] Write(Xoh_hzip_bfr bfr, Xow_wiki wiki, Xoae_page page, Xoh_page hpg, Xoh_hzip_mgr hzip_mgr, Io_stream_zip_mgr zip_mgr, int zip_tid, int hzip_tid, byte[] src) {
switch (hzip_tid) {
case Xoh_hzip_dict_.Hzip__none:
update_mgr.Parse(hpg, wiki, page.Url_bry_safe(), src);
src = hpg.Db().Html().Html_bry();
break;
case Xoh_hzip_dict_.Hzip__v1:
src = hzip_mgr.Encode_as_bry((Xoh_hzip_bfr)bfr.Clear(), wiki, hpg, src);
break;
}
src_as_hzip = src;
if (zip_tid > gplx.core.ios.streams.Io_stream_tid_.Tid__raw)
src = zip_mgr.Zip((byte)zip_tid, src);

View File

@ -40,6 +40,7 @@ public class Xob_hdump_bldr implements Gfo_invk {
this.toc_label = wiki.Msg_mgr().Val_by_id(gplx.xowa.langs.msgs.Xol_msg_itm_.Id_toc);
if (zip_tid == Byte_.Max_value_127) zip_tid = Xobldr_cfg.Zip_mode__html(wiki.App());
hdump_mgr.Init_by_app(wiki.Appe());
hdump_mgr.Init_by_db(zip_tid, hzip_enabled, hzip_b256);
return true;
}
@ -63,7 +64,7 @@ public class Xob_hdump_bldr implements Gfo_invk {
// save to db
Xowd_html_tbl html_tbl = html_tbl_retriever.Get_html_tbl(wpg.Ttl().Ns(), prv_row_len); // get html_tbl
this.prv_row_len = hdump_mgr.Save_mgr().Save(tmp_hpg.Ctor_by_hdiff(tmp_bfr, wpg, toc_label), html_tbl, true, is_wikitext); // save to db
this.prv_row_len = hdump_mgr.Save_mgr().Save(wpg, tmp_hpg.Ctor_by_hdiff(tmp_bfr, wpg, toc_label), html_tbl, true, is_wikitext); // save to db
stat_tbl.Insert(tmp_hpg, stat_itm, wpg.Root().Root_src().length, tmp_hpg.Db().Html().Html_bry().length, prv_row_len); // save stats
// run hzip diff if enabled

View File

@ -51,9 +51,9 @@ public class Xoh_hzip_dict_ {
, Key__pgbnr = "pgbnr"
, Key__media = "media"
;
public static final int // SERIALIZED
Hzip__none = 0
, Hzip__v1 = 1
, Hzip__plain = 2 // used for page_sync
;
public static final int // SERIALIZED:html_db.html.body_flag
Hzip__none = 0
, Hzip__v1 = 1
, Hzip__plain = 2 // used for page_sync
;
}

View File

@ -20,8 +20,8 @@ import gplx.xowa.htmls.core.hzips.*;
import gplx.xowa.htmls.core.wkrs.hdrs.*; import gplx.xowa.htmls.core.wkrs.imgs.*;
public class Xoh_hdoc_wkr__make implements Xoh_hdoc_wkr {
private Xoh_hzip_bfr bfr; private Xoh_page hpg; private Xoh_hdoc_ctx hctx; private byte[] src;
private final Xoh_hdr_wtr wkr__hdr = new Xoh_hdr_wtr();
private final Xoh_img_wtr wkr__img = new Xoh_img_wtr();
private final Xoh_hdr_wtr wkr__hdr = new Xoh_hdr_wtr();
private final Xoh_img_wtr wkr__img = new Xoh_img_wtr();
public void On_new_page(Xoh_hzip_bfr bfr, Xoh_page hpg, Xoh_hdoc_ctx hctx, byte[] src, int src_bgn, int src_end) {
this.bfr = bfr; this.hpg = hpg; this.hctx = hctx; this.src = src;
}
@ -29,16 +29,24 @@ public class Xoh_hdoc_wkr__make implements Xoh_hdoc_wkr {
public void On_escape (gplx.xowa.htmls.core.wkrs.escapes.Xoh_escape_data data) {bfr.Add(data.Hook());}
public void On_xnde (gplx.xowa.htmls.core.wkrs.xndes.Xoh_xnde_parser data) {bfr.Add_mid(src, data.Src_bgn(), data.Src_end());}
public void On_lnki (gplx.xowa.htmls.core.wkrs.lnkis.Xoh_lnki_data data) {bfr.Add_mid(src, data.Src_bgn(), data.Src_end());}
public void On_thm (gplx.xowa.htmls.core.wkrs.thms.Xoh_thm_data data) {bfr.Add_mid(src, data.Src_bgn(), data.Src_end());}
public void On_gly (gplx.xowa.htmls.core.wkrs.glys.Xoh_gly_grp_data data) {}
public void On_thm (gplx.xowa.htmls.core.wkrs.thms.Xoh_thm_data data) {
Xoh_img_data img_data = (gplx.xowa.htmls.core.wkrs.imgs.Xoh_img_data)data.Img_data();
bfr.Add_mid(src, data.Src_bgn(), img_data.Src_bgn());
wkr__img.Init_by_parse(bfr, hpg, hctx, src, img_data);
bfr.Add_mid(src, img_data.Src_end(), data.Src_end());
}
public void On_gly (gplx.xowa.htmls.core.wkrs.glys.Xoh_gly_grp_data data) {
bfr.Add_mid(src, data.Src_bgn(), data.Src_end());
}
public boolean Process_parse(Xoh_data_itm data) {
switch (data.Tid()) {
case Xoh_hzip_dict_.Tid__img: wkr__img.Init_by_parse(bfr, hpg, hctx, src, (gplx.xowa.htmls.core.wkrs.imgs.Xoh_img_data)data); return true;
case Xoh_hzip_dict_.Tid__hdr: wkr__hdr.Init_by_parse(bfr, hpg, hctx, src, (gplx.xowa.htmls.core.wkrs.hdrs.Xoh_hdr_data)data); return true;
case Xoh_hzip_dict_.Tid__lnke: break;
default: throw Err_.new_unhandled(data.Tid());
case Xoh_hzip_dict_.Tid__img: return wkr__img.Init_by_parse(bfr, hpg, hctx, src, (gplx.xowa.htmls.core.wkrs.imgs.Xoh_img_data)data);
case Xoh_hzip_dict_.Tid__hdr: return wkr__hdr.Init_by_parse(bfr, hpg, hctx, src, (gplx.xowa.htmls.core.wkrs.hdrs.Xoh_hdr_data)data);
case Xoh_hzip_dict_.Tid__lnke:
default:
bfr.Add_mid(src, data.Src_bgn(), data.Src_end());
break;
}
bfr.Add_mid(src, data.Src_bgn(), data.Src_end());
return true;
}
}

View File

@ -41,7 +41,7 @@ public abstract class Xoh_itm_parser_fxt {
Xoh_page hpg = new Xoh_page(); // NOTE: no need to pass url and ttl now
hctx.Init_by_page(wiki, hpg);
err_wkr.Init_by_page(Xoa_page_.Main_page_str, src);
Exec_parse_hook(err_wkr, hctx, 0, src_len);
Exec_parse_hook(err_wkr, hctx, src, 0, src_len);
}
public abstract void Exec_parse_hook(Bry_err_wkr err_wkr, Xoh_hdoc_ctx hctx, int src_bgn, int src_end);
public abstract void Exec_parse_hook(Bry_err_wkr err_wkr, Xoh_hdoc_ctx hctx, byte[] src, int src_bgn, int src_end);
}

View File

@ -20,9 +20,10 @@ import gplx.xowa.htmls.sections.*; import gplx.xowa.htmls.core.hzips.*;
public class Xoh_hdr_wtr implements gplx.core.brys.Bfr_arg, Xoh_wtr_itm {
private int hdr_num; private byte[] hdr_id, hdr_content, hdr_capt_rhs;
private Xoh_page hpg;
public void Init_by_parse(Bry_bfr bfr, Xoh_page hpg, Xoh_hdoc_ctx hctx, byte[] src, Xoh_hdr_data data) {
Init_by_decode(hpg, hctx, src, data);
public boolean Init_by_parse(Bry_bfr bfr, Xoh_page hpg, Xoh_hdoc_ctx hctx, byte[] src, Xoh_hdr_data data) {
if (!Init_by_decode(hpg, hctx, src, data)) return false;
this.Bfr_arg__add(bfr);
return true;
}
public boolean Init_by_decode(Xoh_page hpg, Xoh_hdoc_ctx hctx, byte[] src, Xoh_data_itm data_itm) {
this.hpg = hpg;

View File

@ -56,9 +56,10 @@ public class Xoh_img_wtr implements Bfr_arg, Xoh_wtr_itm {
}
public Xoh_img_wtr Anch_cls_(byte[] v) {anch_cls.Set_by_bry(v); return this;}
public Xoh_img_wtr Img_id_(int uid) {img_id.Set(uid); return this;}
public void Init_by_parse(Bry_bfr bfr, Xoh_page hpg, Xoh_hdoc_ctx hctx, byte[] src, Xoh_img_data data) {
Init_by_decode(hpg, hctx, src, data);
public boolean Init_by_parse(Bry_bfr bfr, Xoh_page hpg, Xoh_hdoc_ctx hctx, byte[] src, Xoh_img_data data) {
if (!Init_by_decode(hpg, hctx, src, data)) return false;
this.Bfr_arg__add(bfr);
return true;
}
public void Init_html(int html_w, int html_h, byte[] src_bry) {
img_w.Set_by_int(html_w);
@ -98,12 +99,13 @@ public class Xoh_img_wtr implements Bfr_arg, Xoh_wtr_itm {
else if (data.Img_w() != -1) { // orig exists or some hard-coded image (hiero)
Xoh_img_src_data img_src_data = data.Img_src();
this.Init_html(data.Img_w(), data.Img_h(), img_src_data.Src_bry());
byte[] img_src_bry = img_src_data.Src_mid();
this.Init_html(data.Img_w(), data.Img_h(), img_src_bry);
int file_w = data.Img_src().File_w();
// NOTE: init lnki with "64|file_w|-1|-1|-1|-1"; DATE:2016-08-10
fsdb_itm.Init_at_lnki(Xof_exec_tid.Tid_wiki_page, hctx.Cache__wiki_abrv(img_src_data.Repo_is_commons()), lnki_ttl, Xop_lnki_type.Tid_orig_known, Xop_lnki_tkn.Upright_null, file_w, Xof_img_size.Null, data.Img_src().File_time(), data.Img_src().File_page(), Xof_patch_upright_tid_.Tid_all);
fsdb_itm.Init_at_gallery_bgn(data.Img_w(), data.Img_h(), file_w);
fsdb_itm.Html_view_url_(Io_url_.New__http_or_fail(img_src_data.Src_bry()));
fsdb_itm.Html_view_url_(Io_url_.New__http_or_fail(img_src_bry));
fsdb_itm.File_is_orig_(data.Img_src().File_is_orig());
// ASSUME: if file_w != img_w, then page has packed gallery; PAGE:en.w:Mexico; DATE:2016-08-14

View File

@ -45,6 +45,7 @@ public class Xoh_img_cls_data implements Bfr_arg_clearable {
if (pos < src_end && src[pos] == Byte_ascii.Space)
++pos;
if (cls_tid == Xoh_img_cls_.Tid__manual || pos < src_end) {
this.src = atr.Src(); // set src, else NPE when trying to write to bfr; DATE:2019-01-04
this.other_bgn = pos;
this.other_end = src_end;
}

View File

@ -21,9 +21,10 @@ import gplx.xowa.wikis.domains.*;
public class Xoh_img_src_data implements Bfr_arg_clearable, Xoh_itm_parser {
private final Bry_rdr rdr = new Bry_rdr().Dflt_dlm_(Byte_ascii.Slash);
private boolean fail_throws_err;
public byte[] Src_bry() {return src_bry;} private byte[] src_bry;
private byte[] src_bry;
public int Src_bgn() {return src_bgn;} private int src_bgn;
public int Src_end() {return src_end;} private int src_end;
public byte[] Src_mid() {return src_mid;} private byte[] src_mid;
public int Repo_bgn() {return repo_bgn;} private int repo_bgn;
public int Repo_end() {return repo_end;} private int repo_end;
public boolean Repo_is_commons() {return repo_is_commons;} private boolean repo_is_commons;
@ -49,13 +50,14 @@ public class Xoh_img_src_data implements Bfr_arg_clearable, Xoh_itm_parser {
public boolean Parse(Bry_err_wkr err_wkr, Xoh_hdoc_ctx hctx, byte[] domain_bry, Gfh_tag tag) {
this.Clear();
Gfh_atr atr = tag.Atrs__get_by_or_empty(Gfh_atr_.Bry__src);
return Parse(err_wkr, hctx, domain_bry, atr.Val_bgn(), atr.Val_end());
return Parse(err_wkr, hctx, domain_bry, atr.Src(), atr.Val_bgn(), atr.Val_end());
}
public boolean Parse(Bry_err_wkr err_wkr, Xoh_hdoc_ctx hctx, byte[] domain_bry, int src_bgn, int src_end) { // EX: src="file:///C:/xowa/file/commons.wikimedia.org/thumb/7/0/1/2/A.png/220px.png"
public boolean Parse(Bry_err_wkr err_wkr, Xoh_hdoc_ctx hctx, byte[] domain_bry, byte[] src_bry, int src_bgn, int src_end) { // EX: src="file:///C:/xowa/file/commons.wikimedia.org/thumb/7/0/1/2/A.png/220px.png"
this.Clear();
this.src_bry = err_wkr.Src();
this.src_bry = src_bry;
this.src_bgn = src_bgn; this.src_end = src_end;
if (src_end == src_bgn) return true; // empty src; just return true;
this.src_mid = Bry_.Mid(src_bry, src_bgn, src_end);
// get repo_bgn; note that some <img> may be hiero / enlarge / magnify and should exit
rdr.Init_by_wkr(err_wkr, "img.src.xowa", src_bgn, src_end).Fail_throws_err_(fail_throws_err);

View File

@ -59,8 +59,8 @@ class Xoh_img_src_data_fxt extends Xoh_itm_parser_fxt { private final Xoh_im
Tfds.Eq_double(expd_time, parser.File_time());
Tfds.Eq_int(expd_page, parser.File_page());
}
@Override public void Exec_parse_hook(Bry_err_wkr err_wkr, Xoh_hdoc_ctx hctx, int src_bgn, int src_end) {
@Override public void Exec_parse_hook(Bry_err_wkr err_wkr, Xoh_hdoc_ctx hctx, byte[] src, int src_bgn, int src_end) {
parser.Fail_throws_err_(true);
parser.Parse(err_wkr, new Xoh_hdoc_ctx(), Xow_domain_itm_.Bry__enwiki, src_bgn, src_end);
parser.Parse(err_wkr, new Xoh_hdoc_ctx(), Xow_domain_itm_.Bry__enwiki, src, src_bgn, src_end);
}
}

View File

@ -54,7 +54,7 @@ class Xoh_anch_href_data_fxt extends Xoh_itm_parser_fxt { private final Xoh_
Tfds.Eq_str(expd_site, parser.Site_bgn() == -1 ? "" : String_.new_u8(src, parser.Site_bgn(), parser.Site_end()));
Tfds.Eq_str(expd_page, String_.new_u8(src, parser.Ttl_bgn(), parser.Ttl_end()));
}
@Override public void Exec_parse_hook(Bry_err_wkr err_wkr, Xoh_hdoc_ctx hctx, int src_bgn, int src_end) {
parser.Parse(err_wkr, hctx, err_wkr.Src(), src_bgn, src_end);
@Override public void Exec_parse_hook(Bry_err_wkr err_wkr, Xoh_hdoc_ctx hctx, byte[] src, int src_bgn, int src_end) {
parser.Parse(err_wkr, hctx, src, src_bgn, src_end);
}
}