flnews_post_proc 1.41 → 1.44

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6d1a635207d4ca4d8fa516c00b23716f0446fa015bd26527483686895a4d37a8
-  data.tar.gz: 99a27fa42f530982a3854fb783f69146fdf62a4910f0145dc7551a4e6d7ec4b2
+  metadata.gz: dd6a768ede3aff691558eba80a8a4b63df2ee0a9ca06e9c5686d71d3512dd29d
+  data.tar.gz: c068b97b1648e39f7ed02d774f301157e69cf065702556605acf777ab40782db
 SHA512:
-  metadata.gz: ef0f0e4c3e3b04cb1c3c1b3213ec4ef2d7c5ec8909bd7d22d581269953c4a1283c5263680990d0ff5a085077f01ddbc8b2808f90b0052c8bbbb169bae8d9622a
-  data.tar.gz: 387191fb0c3bdc9c434c970ee2b72de669dbd9d66791eb8a65c987e7ef3b6d523e39d56ebbdf2c2471bcd9897060f151c3c710bd6d03f6eeb7694e621c03e1b6
+  metadata.gz: c01e7ed3b8174bc4707b9b00842c684f9b0c389551a7a66ec5f95ccd3fbf775bd9e8bd34e700e9a5cedf07bc826fec7d7d7b7c62324222e2fcf217637226a955
+  data.tar.gz: 51704cb9e8bb5c1967efc09fce01e60be87bc0e88af79542bb9aef31ed0cf7f92a9283d2e3850ac19330935e46613f4aad1f506d89acf21248d92b21bdfffaaa

data/README.md

@@ -93,14 +93,14 @@ some users may not always agree with the result and for arbitrary reasons:
   Custom headers may be defined in the configuration file for the program  
   and will then be added to each outgoing post.
 
-* The X-No-Archive header is sometimes set to avoid that an article be  
-  saved and stays available to search-engines (Google, notably). Test-  
-  postings, for example, do probably not justify at all that they would be  
-  referenced in search results.  
-  The post-processor program can impose the X-No-Archive header for all  
-  posts to certain newsgroups.
+* The Archive- and X-No-Archive headers are sometimes set to avoid that an
+  article be saved and stays available to search-engines (Google, notably).
+  Test-  postings, for example, do probably not justify at all that they would
+  be  referenced in search results. The post-processor program can impose the
+  Archive- and X-No-Archive header for all posts to certain newsgroups.
 
-  **ATTN** As of 2024, this header might serve no purpose any more.
+  **ATTN** As of 2024, the X-No-Archive has lost most of its utility and it 
+  is the decision of server operators to honor it or not.
 
 * If a news post contains many references to either other posts or Web  
   pages, the text can be cluttered with URLs.  
@@ -129,7 +129,7 @@ have not yet been set in the configuration.
 * Signatures, as set in the configuration **can be ignored**. Either  
   a default signature will appear as set in flnews or none.  
 * Custom Headers, if configured, can be **omitted**.  
-* The X-No-Archive header, if set for the current newsgroup, **can be  
+* Archive- and X-No-Archive headers, if set for the current newsgroup, **can be
   ignored**.  
 * The verification & correction of references **can be disabled**.  
 * Logging can be **switched off**, if set.
@@ -225,9 +225,10 @@ intact.
   _\- 'X-My-Header: nothing fancy'_  
   _\- 'X-Another-Header: care not!'_ 
 
-**XNAY_GROUPS**  
- The newsgroups, where a header X-No-Archive: YES shall be set.
- **ATTN** As of 2024, this header might serve no purpose any more.
+**NO_ARCHIVE_GROUPS**  
+
+ The newsgroups, where the headers “Archive: no” and “X-No-Archive: YES” shall
+ be set.  
 
  CONTENT: a dash and space, then a String, containing the name of the group or   
  a regexp.

data/bin/flnews_post_proc

@@ -2,7 +2,7 @@
 #encoding: UTF-8
 =begin
 /***************************************************************************
- *   ©2023-2023, Michael Uplawski <michael.uplawski@uplawski.eu>           *
+ *   ©2023-2024, Michael Uplawski <michael.uplawski@uplawski.eu>           *
  *                                                                         *
  *   This program is free software; you can redistribute it and/or modify  *
  *   it under the terms of the DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE *
@@ -26,8 +26,14 @@ require_relative '../lib/override'
 require_relative '../lib/flnews_post_proc'
 require_relative '../lib/basic_logging'
 require_relative '../lib/configuration'
+require_relative '../lib/version'
 
 self.extend(BasicLogging)
+
+msg = PROGNAME.dup << ' ' << PROGVERSION << ' starting' 
+msg = "–––––– " << msg << " ––––––"
+
+info msg
 # Get a configuration 
 config = Configuration::instance
 
@@ -80,5 +86,4 @@ else
   STDERR.puts usage
   exit false 
 end
-
 # Ω

data/doc/html/flnews_post_proc.html

@@ -390,38 +390,33 @@ own creations.</p>
 <h2>The limits of a basic newsreader — what the program can do</h2>
 <p>While the articles that flnews creates, are complete and ready to be posted,
 some users may not always agree with the result and for arbitrary reasons:</p>
-<ul>
-<li><p class="first">There may be inconveniences when you post to different newsgroups in
+<ul class="simple">
+<li>There may be inconveniences when you post to different newsgroups in
 different languages, as an introductory line which refers to a previous
 post can only be set once in the flnews-configuration. The consequence
 can be that your post to a french newsgroup begins with an introduction
 in English.
 My post-processor program can set an introductory line specifically
-chosen for one or several newsgroups.</p>
-</li>
-<li><p class="first">The same conflict arises, when you have set a standard signature-text and
+chosen for one or several newsgroups.</li>
+<li>The same conflict arises, when you have set a standard signature-text and
 would like to replace it against another, based on the newsgroup you are
 about to post to.
 The post-processor program sets specific signatures as configured for one
-or several newsgroups.</p>
-</li>
-<li><p class="first">Some custom headers may serve to convey additional information to
+or several newsgroups.</li>
+<li>Some custom headers may serve to convey additional information to
 interested readers of your post, like GnuPG key IDs, your language skills
 or the like. The signature may be a better choice than custom headers.
 You are free. I just mention face and x-face but prefer that you do not
 remember I did.
 Custom-headers may be defined in the configuration file for the program
-and will then be added to each outgoing post.</p>
-</li>
-<li><p class="first">The X-No-Archive header is sometimes set to avoid that an article be
-saved and stays available to search-engines (Google, notably). Test-
-postings, for example, do probably not justify at all that they would be
-referenced in search-results.
-The post-processor program can impose the X-No-Archive header for all
-posts to certain newsgroups.</p>
-<p><strong>ATTN</strong> Since 2024, this header might no longer serve any purpose.</p>
-</li>
-<li><p class="first">If a news post contains many references to either other posts or Web
+and will then be added to each outgoing post.</li>
+<li>The Archive- and the X-No-Archive header are sometimes set to avoid that an
+article be saved and stays available to search-engines (Google, notably).
+Test- postings, for example, do probably not justify at all that they would
+be referenced in search-results.
+The post-processor program can impose both headers for all posts to certain
+newsgroups.</li>
+<li>If a news post contains many references to either other posts or Web
 pages, the text can be cluttered with URLs.
 The post-processor can identify marked text fragments and transform them
 into footnotes, which will be attached as a list at the bottom of the
@@ -430,8 +425,7 @@ This works almost like the &lt;ref/&gt; link in Wikipedia, but the delimiter
 can be determined in the configuration file.
 Example (with %=):
 This is an object %=and this becomes the footnote, describing the object
-further=%</p>
-</li>
+further=%</li>
 </ul>
 </div>
 <div class="section" id="dialog-to-override-settings">
@@ -445,8 +439,8 @@ have not yet been set in the configuration.</p>
 <li>Signatures, as set in the configuration <strong>can be ignored</strong>. Either
 a default signature will appear as set in flnews or none.</li>
 <li>Custom Headers, if configured, can be <strong>omitted</strong>.</li>
-<li>The X-No-Archive header, if set for the current newsgroup, <strong>can be
-ignored</strong>.</li>
+<li>The Archive- and X-No-Archive headers, if set for the current newsgroup,
+<strong>can be ignored</strong>.</li>
 <li>Logging can be <strong>switched off</strong>, if set.</li>
 </ul>
 <p>Pushing Esc or the cancle-button of the dialog interrupts the process, flnews
@@ -523,9 +517,9 @@ name of the header, ending in a colon and the value of the header.</p>
 <div class="line">- 'X-Another-Header: care not!'</div>
 </div>
 </dd>
-<dt><strong>XNAY_GROUPS</strong></dt>
-<dd><p class="first">The newsgroups, where a header X-No-Archive: YES shall be set.
-<strong>ATTN</strong> Since 2024, this header might no longer serve any purpose.</p>
+<dt><strong>NO_ARCHIVE_GROUPS</strong></dt>
+<dd><p class="first">The newsgroups, where the headers “Archive: no” and “X-No-Archive: YES” shall
+be set.</p>
 <p>CONTENT: a dash and space, then a String, containing the name of the group or a regexp.</p>
 <p>DEFAULT: empty</p>
 <div class="last line-block">

data/doc/html/flnews_post_proc_fr.html

@@ -421,14 +421,14 @@ ne vous en souvenez pas.</p>
 <p>Ces entêtes, – Custom-Headers – peuvent être définis dans la configuration
 du logiciel et vont être utilisées dans chaque article sortant.</p>
 </li>
-<li><p class="first">L'entête « X-No-Archive » est parfois utilisé afin d'éviter l'archivage
-d'un article. Il ne devrait par conséquence pas être trouvé par les moteurs
-de recherche ( Google notamment ). Les articles dans les groupes de test, par
-exemple, ne valent probablement pas qu'on les trouve parmi les résultats des
-recherches.</p>
+<li><p class="first">Les entêtes « Archive » et « X-No-Archive » sont parfois utilisés afin
+d'éviter l'archivage d'un article. Il ne devrait par conséquence pas être
+trouvé par les moteurs de recherche ( Google notamment ). Les articles dans
+les groupes de test, par exemple, ne valent probablement pas qu'on les trouve
+parmi les résultats des recherches.</p>
 <p>Avec flnews_post_proc vous pouvez décider et imposer que vos articles dans
-certains newsgroups contiendront d'office une entête <strong>X-No-Archive: Yes</strong>.</p>
-<p><strong>ATTN</strong> Depuis l'année 2024, cet entête n'a probablement plus de fonction.</p>
+certains newsgroups contiendront d'office les deux entêtes <strong>Archive: no</strong> et
+<strong>X-No-Archive: Yes</strong>.</p>
 </li>
 <li><p class="first">Certains messages mentionnent d'autres articles ou des URLs de pages Web.
 S'ils sont nombreux, ces références peuvent déranger la lecture à cause de
@@ -456,7 +456,8 @@ des options, qui ne l'ont pas été auparavant :</p>
 <li>Signatures, comme définis dans la configuration <strong>peuvent être ignorées</strong>.
 Soit une signature par défaut sera appliquée, si prévue, ou aucune.</li>
 <li>Entêtes supplémentaires, si définis, peuvent rester absentes de l'article.</li>
-<li>L'entête X-No-Archive, si prévu pour le newsgroup choisi, peut être ignoré.</li>
+<li>Les entêtes Archive et X-No-Archive, si prévus pour le newsgroup choisi,
+peuvent être ignorés.</li>
 <li>L'auto correction de URLs et références à d'autres articles peut être
 désactivé.</li>
 <li>L'écriture d'un protocole peut être arrêtée.</li>
@@ -550,9 +551,9 @@ l'entête.</p>
 <div class="line">- 'X-Another-Header: care not!'</div>
 </div>
 </dd>
-<dt><strong>XNAY_GROUPS</strong></dt>
-<dd><p class="first">Les newsgroups, où une entête X-No-Arcive: YES doit être présent.
-<strong>ATTN</strong> Depuis l'année 2024, cet entête n'a probablement plus de fonction.</p>
+<dt><strong>NO_ARCHIVE_GROUPS</strong></dt>
+<dd><p class="first">Les newsgroups, où les entêtes « Archive: no » et « X-No-Archive: yes »
+doivent être présents.</p>
 <p>CONTENU : Un trait d'union et un espace, puis une chaîne de caractères,
 contenant le nom du groupe ou une expression.</p>
 <p>PAR DÉFAUT : Vide</p>

data/doc/rst/flnews_post_proc.rst

@@ -60,14 +60,12 @@ some users may not always agree with the result and for arbitrary reasons:
   Custom-headers may be defined in the configuration file for the program
   and will then be added to each outgoing post.
 
-* The X-No-Archive header is sometimes set to avoid that an article be
-  saved and stays available to search-engines (Google, notably). Test-
-  postings, for example, do probably not justify at all that they would be
-  referenced in search-results.
-  The post-processor program can impose the X-No-Archive header for all
-  posts to certain newsgroups.
-
-  **ATTN** Since 2024, this header might no longer serve any purpose.
+* The Archive- and the X-No-Archive header are sometimes set to avoid that an
+  article be saved and stays available to search-engines (Google, notably).
+  Test- postings, for example, do probably not justify at all that they would
+  be referenced in search-results.
+  The post-processor program can impose both headers for all posts to certain
+  newsgroups.
 
 * If a news post contains many references to either other posts or Web
   pages, the text can be cluttered with URLs.
@@ -91,8 +89,8 @@ have not yet been set in the configuration.
 * Signatures, as set in the configuration **can be ignored**. Either
   a default signature will appear as set in flnews or none.
 * Custom Headers, if configured, can be **omitted**.
-* The X-No-Archive header, if set for the current newsgroup, **can be
-  ignored**.
+* The Archive- and X-No-Archive headers, if set for the current newsgroup,
+  **can be ignored**.
 * Logging can be **switched off**, if set.
 
 Pushing Esc or the cancle-button of the dialog interrupts the process, flnews
@@ -187,9 +185,9 @@ categories:
  | - 'X-My-Header: nothing fancy'
  | - 'X-Another-Header: care not!' 
 
-**XNAY_GROUPS**
- The newsgroups, where a header X-No-Archive: YES shall be set.
- **ATTN** Since 2024, this header might no longer serve any purpose.
+**NO_ARCHIVE_GROUPS** 
+ The newsgroups, where the headers “Archive: no” and “X-No-Archive: YES” shall
+ be set.
 
  CONTENT: a dash and space, then a String, containing the name of the group or a regexp.
 

data/doc/rst/flnews_post_proc_fr.rst

@@ -73,16 +73,15 @@ et ce pour des raisons arbitraires :
   Ces entêtes, – Custom-Headers – peuvent être définis dans la configuration
   du logiciel et vont être utilisées dans chaque article sortant.
 
-* L'entête « X-No-Archive » est parfois utilisé afin d'éviter l'archivage
-  d'un article. Il ne devrait par conséquence pas être trouvé par les moteurs
-  de recherche ( Google notamment ). Les articles dans les groupes de test, par
-  exemple, ne valent probablement pas qu'on les trouve parmi les résultats des
-  recherches.
+* Les entêtes « Archive » et « X-No-Archive » sont parfois utilisés afin
+  d'éviter l'archivage d'un article. Il ne devrait par conséquence pas être
+  trouvé par les moteurs de recherche ( Google notamment ). Les articles dans
+  les groupes de test, par exemple, ne valent probablement pas qu'on les trouve
+  parmi les résultats des recherches.
 
   Avec flnews_post_proc vous pouvez décider et imposer que vos articles dans
-  certains newsgroups contiendront d'office une entête **X-No-Archive: Yes**.
-
-  **ATTN** Depuis l'année 2024, cet entête n'a probablement plus de fonction.
+  certains newsgroups contiendront d'office les deux entêtes **Archive: no** et
+  **X-No-Archive: Yes**.
 
 * Certains messages mentionnent d'autres articles ou des URLs de pages Web.
   S'ils sont nombreux, ces références peuvent déranger la lecture à cause de
@@ -112,7 +111,8 @@ des options, qui ne l'ont pas été auparavant :
 
 * Entêtes supplémentaires, si définis, peuvent rester absentes de l'article.
 
-* L'entête X-No-Archive, si prévu pour le newsgroup choisi, peut être ignoré.
+* Les entêtes Archive et X-No-Archive, si prévus pour le newsgroup choisi,
+  peuvent être ignorés.
 
 * L'auto correction de URLs et références à d'autres articles peut être
   désactivé. 
@@ -218,9 +218,9 @@ variables définis dans ce fichier peuvent être classées en deux catégories :
  | - 'X-My-Header: nothing fancy'
  | - 'X-Another-Header: care not!' 
 
-**XNAY_GROUPS**
- Les newsgroups, où une entête X-No-Arcive: YES doit être présent.  
- **ATTN** Depuis l'année 2024, cet entête n'a probablement plus de fonction.
+**NO_ARCHIVE_GROUPS**
+ Les newsgroups, où les entêtes « Archive: no » et « X-No-Archive: yes »
+ doivent être présents.
 
  CONTENU : Un trait d'union et un espace, puis une chaîne de caractères,
  contenant le nom du groupe ou une expression.

data/lib/_quoting_style_regexp

@@ -0,0 +1 @@
+" > >> > testerei ei ei".strip.gsub( /^>+(\s+>+)*/) {|m| m.to_s.delete(" ")}

data/lib/body.rb

@@ -203,19 +203,23 @@ class Body
   # handle <news:..@...>
   def handle_news(l)
     # ... “Do not trust nobody!”
-    if l.include?('@') && ! l.include?('http:') 
+    if l.include?('@') && ! l.include?('http:') && ! l.include?('https:') 
       # And I forgot how this works. It does.
       l.split.collect do |ele| 
         # angular brackets are there alright. Hurra. 
         url = ele.match(/\<(.*)\>/)
         unless !url
           debug(' with angular brackets: ' << url.inspect)
-          l = l.sub(url[1], 'news:' << url[1]) if !url[1].include?('mailto')
+          l = l.sub(url[1], 'news:' << url[1]) if !url[1].start_with?('mailto') && !url[1].start_with?('news')
         else
           url = ele.match(/\S+@(\.|[^\p{P}]+)\S+/)
           if url
             debug(' withOUT angular brackets: ' << url.inspect)
-            l = l.sub(url[0], '<news:' << url[0] << '>') if !url[0].include?('mailto')
+            if !url[0].start_with?('mailto') && !url[0].start_with?('news')
+              l.sub!(url[0], 'news:' << url[0] )          
+            end
+            l.sub!('news:', '<news:')
+            l.sub!(url[0], url[0] << '>')
           end
         end
       end # url_strs = collect
@@ -227,7 +231,11 @@ class Body
   def handle_http(l)
     debug('handle http')
     l_array = l.split
-    url_strs = l_array.collect{|ele| ele.strip.include?('http') ? ele.strip : nil}.compact
+    url_strs = l_array.collect do |ele| 
+      if ele.strip.include?('http') && ele.match(/https?:/)
+        ele.strip    
+      end
+    end.compact
     debug('url_strs: ' << url_strs.to_s)
     url_strs.each do |str|
       # keep str for final replacement
@@ -235,13 +243,13 @@ class Body
       debug( 'try to match http-link')
       begin
         # missing slashes ?
-        match = str.match(/(https?):(\/{2})/)
+        match = str.match(/(https?):(\/*)/)
         if (!match || match.length != 3 || match[2] != '//')
-          debug 'cannot find slashes in the URL'
+          debug 'cannot find (enough) slashes in the URL'
           if str.match(/https:/)
-            nstr = str.sub(/https:/, "https://")
+            nstr = str.sub(/https:\/*/, "https://")
           elsif str.match(/http:/)
-            nstr = str.sub(/http:/, "http://") 
+            nstr = str.sub(/http:\/*/, "http://") 
           end
           debug ' with slashes: ' << nstr
         end
@@ -252,8 +260,8 @@ class Body
         match = nstr.match(/\<?(https?:\/\/[^\>]*)\>?/)
         # get the darned URL already!
         url = match[1] if match
-       #  nstr = with_angular_brackets(nstr, url)
-        return l.sub(str, nstr)
+        #  nstr = with_angular_brackets(nstr, url)
+        l.sub!(str, nstr)
       rescue Exception => ex
         # this had looked intelligent, once.
         line = __LINE__
@@ -264,6 +272,8 @@ class Body
         exit false
       end
     end
+
+    return l
   end
 end
 # Ω

data/lib/version.rb

@@ -14,8 +14,8 @@
 =end
 
 PROGNAME = 'flnews_post_proc'
-PROGVERSION = "1.41"
+PROGVERSION = "1.44"
 AUTHORS = "Michael Uplawski"
 EMAIL = "michael.uplawski@uplawski.eu"
 YEARS = "2023 - 2024"
-SUMMARY = "Additional Header 'Archive: no', when No Archive is chosen."
+SUMMARY = "Bugfix: Strings http and https without following colon are not interpreted as links"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: flnews_post_proc
 version: !ruby/object:Gem::Version
-  version: '1.41'
+  version: '1.44'
 platform: ruby
 authors:
 - Michael Uplawski
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-04-18 00:00:00.000000000 Z
+date: 2024-05-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: diffy
@@ -48,6 +48,7 @@ files:
 - doc/pdf/flnews_post_proc_fr.pdf
 - doc/rst/flnews_post_proc.rst
 - doc/rst/flnews_post_proc_fr.rst
+- lib/_quoting_style_regexp
 - lib/basic_logging.rb
 - lib/body.rb
 - lib/color_output.rb
@@ -84,5 +85,6 @@ requirements: []
 rubygems_version: 3.4.20
 signing_key:
 specification_version: 4
-summary: 'Additional Header ''Archive: no'', when No Archive is chosen.'
+summary: 'Bugfix: Strings http and https without following colon are not interpreted
+  as links'
 test_files: []