docs: reading main page name via zimdump info

This requires zim-tools 2.2.0 or later License: MIT Signed-off-by: Marcin Rataj <[email protected]>
ipfs · Feb 12, 2021 · e4f5e18 · e4f5e18
1 parent 866197b
commit e4f5e18
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 27 deletions.
diff --git a/README.md b/README.md
@@ -149,13 +149,28 @@ $ node ./bin/run --help
 
 First though the main page, as the archive appears on the appropriate wikimedia website, must be determined. For instance, the zim file for Turkish Wikipedia has a main page of `Kullanıcı:The_other_Kiwix_guy/Landing` but `https://tr.wikipedia.org` uses `Anasayfa` as the main page. Both must be passed to the node script.
 
-To determine the website main page use `./tools/find_main_page_name.sh` passing the website:
+To determine the original main page use `./tools/find_main_page_name.sh`:
 
-```sh
+```console
 $ ./tools/find_main_page_name.sh tr.wikiquote.org
 Anasayfa
 ```
 
+To determine the main page in ZIM file open in in a [Kiwix reader](https://www.kiwix.org/en/kiwix-reader) or use `zimdump info` (version 2.2.0 or later) and ignore the `A/` prefix:
+
+```console
+$ zimdump info wikipedia_tr_all_maxi_2021-01.zim
+count-entries: 1088190
+uuid: 840fc82f-8f14-e11e-c185-6112dba6782e
+cluster count: 5288
+checksum: 50113b4f4ef5ddb62596d361e0707f79
+main page: A/Kullanıcı:The_other_Kiwix_guy/Landing
+favicon: -/favicon
+
+$ zimdump info wikipedia_tr_all_maxi_2021-01.zim | grep -oP 'main page: A/\K\S+'
+Kullanıcı:The_other_Kiwix_guy/Landing
+```
+
 The conversion is done on the unpacked zim directory:
 
 ```sh

diff --git a/src/article-transforms.ts b/src/article-transforms.ts
@@ -43,32 +43,8 @@ export const appendFooter = ($html: any, options: EnhancedOpts) => {
 }
 
 export const appendHtmlPostfix = (href: string) => {
+  // noop:  .html no longer needed since we switched to zimdump
   return href
-  /*  .html no longer needed since we switched to zimdump
-  if (href.includes('/w/index.php')) {
-    return href
-  }
-
-  const parts = href.split(/[#?]+/)
-
-  if (parts.length === 0) {
-    throw new Error('Unexpected parsing of links')
-  }
-
-  if (parts.length === 1) {
-    if (href.endsWith('.html')) {
-      return href
-    }
-
-    return `${href}.html`
-  }
-
-  if (parts[0].endsWith('.html')) {
-    return href
-  }
-
-  return href.replace(parts[0], `${parts[0]}.html`)
-  */
 }
 
 export const prefixRelativeRoot = (href: string) => {
@@ -83,6 +59,10 @@ export const moveRelativeLinksUpOneLevel = (href: string) => {
   return href.replace('../', '')
 }
 
+export const moveRelativeLinksDownOneLevel = (href: string) => {
+  return href.replace('../', '../../')
+}
+
 export const makeScriptLinksRelativeToWiki = (href: string) => {
   if (!href.startsWith('-/')) {
     return href