flnews_post_proc 1.53 → 1.55

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bb3c498d2cde3e3c4afcd611006857a9b88db02cd27a05fe04ef1cac4448d6bd
-  data.tar.gz: 1fbd7d419082397cb748ad397c168c5ebc55b002e162a2831775677b0289734e
+  metadata.gz: 7893f5a913ec2f1682d699180984ffa61603c01722c7f88edd7840b4f3cce797
+  data.tar.gz: a71ea92cc87014b4f75cd99e01d6bafd6b368cb076e5f1420a9e1105c95b97ff
 SHA512:
-  metadata.gz: 547bfbcea62f28654150632b088ad3f9ff7a48b2df3893fff5849e94f865f1ed2c7c39d97f493320f1a1687247118864a242f760ae8c032f4817c43d70bdc43c
-  data.tar.gz: 34ad4b1054b1308f391a4207222ffd39b407e62184cf38012e46d60cfbe3a375b598477e50ff92d9bec8181cbd15ea79d249bb6d0c535b2bf4e884ba7cea9460
+  metadata.gz: 4606de5db3e9f9ea86777e60135f4e80b5d6437380692e446493752d461a8ff0c5e08b042f14ed3de33f52eb6290a89cbd2443c8d0dcb55e36b6819c20e90462
+  data.tar.gz: 8f9a783124f7ec6a1256488fde0bcead47868621506e8b23a7558aa87cca65881afeb9aa13280257a0bc5a7915917b5c592ee98d5ee2aa4fdd30e0dc25e31208

data/README.md

@@ -7,12 +7,12 @@
 Please give priority to the documentation which is delivered with the gem  
 file, as the markdown syntax plays tricks, sometimes, and I may not be  
 quick enough to correct this file. This applies especially to the section   
-[_Configuration_](#CONFIGURATION), below.
+[_Configuration_](#CONFIGURATION), below.  
 
-The gem-file contains different formats of the man-page in English and French.
-See section [_Source Code_](Source-Code), below, for instructions to access
-these texts.  Or see the same files [on the
-Web](https://www.uplawski.eu/div/flnews/).
+The gem-file contains different formats of the man-page in English and French. 
+See section [_Source Code_](Source-Code), below, for instructions to access 
+these texts.  Or see the same files [on the  
+Web](https://www.uplawski.eu/div/flnews/). 
 
 SYNOPSIS
 =======================
@@ -157,6 +157,11 @@ categories:
 
 * Variables defining the new or altered content.  
 
+*ATTENTION*: Most problems that occurred with recent versions of
+*flnews_post_proc* were caused by inadequate option values and very often ill
+chosen or mal formatted regular expressions. PSE double check your
+configuration, if the program does not seem to work normally.
+
 **FUP_NAME**   
 A Regular Expression, describing the string which contains the name of  
 previous poster who is the author of a quoted post.  This string is  

data/bin/flnews_post_proc

@@ -23,6 +23,7 @@ if ! /linux/ =~ RUBY_PLATFORM
 end
 
 require 'tempfile'
+require 'filemagic'
 require_relative '../lib/override'
 require_relative '../lib/flnews_post_proc'
 require_relative '../lib/basic_logging'
@@ -31,6 +32,15 @@ require_relative '../lib/version'
 
 self.extend(BasicLogging)
 
+def usage
+  usage = "\nWhat do you want me to do? Where is the article to post-process?"
+  usage << "\nUsage: "
+  usage << "\n\t#{$0} < article.text"
+  info usage
+  STDERR.puts usage
+  exit false 
+end
+
 msg = PROGNAME.dup << ' ' << PROGVERSION << ' starting' 
 msg = "–––––– " << msg << " ––––––"
 info msg
@@ -44,46 +54,48 @@ config = Configuration::instance
 if (!STDIN.tty?)
   # read from STDIN
   artext = ARGF.read
-  # There is content, create the post-processor.
-  if !artext.strip.empty?
-    #----------->
-    # Allow to override the configuration,
-    # if not disabled (default is true)
-    if config.OVERRIDE_CONFIG != false
-      cdlg = OverrideDlg.new
-      discarded = cdlg.show
-      if discarded && !discarded.empty?    
-        debug('options overriden ' << discarded)
-        OverrideDlg.cvars.each do |v|    
-          if discarded.include?(v.to_s)
-            debug('removing ' << v.to_s)
-            config.set(v, nil)
+
+   # There is content, create the post-processor.
+  if !artext.strip.empty? 
+    mime = FileMagic.mime.buffer artext
+    debug('mime is ' << mime)
+    if mime.start_with?('message/news')  
+      #----------->
+      # Allow to override the configuration,
+      # if not disabled (default is true)
+      if config.OVERRIDE_CONFIG != false
+        cdlg = OverrideDlg.new
+        discarded = cdlg.show
+        if discarded && !discarded.empty?    
+          debug('options overriden ' << discarded)
+          OverrideDlg.cvars.each do |v|    
+            if discarded.include?(v.to_s)
+              debug('removing ' << v.to_s)
+              config.set(v, nil)
+            end
           end
         end
+        debug('new config: ' << config.inspect)
       end
-      debug('new config: ' << config.inspect)
-    end
-    #<--------------
-    pp = PostProcessor.new(artext)    
-    # ... and print its result.
-    article = pp.article
-    if article 
-      # -------------> The main objective <------
-      puts article
-      # <------------- over and out ------>
-      exit true
+      #<--------------
+      pp = PostProcessor.new(artext)    
+      # ... and print its result.
+      article = pp.article
+      if article 
+        # -------------> The main objective <------
+        puts article
+        # <------------- over and out ------>
+        exit true
+      end
+      # whatever.
+      exit false
+    else 
+      error ("Input is of wrong mime-type" << mime)
     end
-    # whatever.
-    exit false
   else
-    error( "Cannot read the article, no content" )
+    error( "Cannot read the article, no content" ) 
   end
 else
-  usage = "\nWhat do you want me to do? Where is the article to post-process?"
-  usage << "\nUsage: "
-  usage << "\n\t#{$0} < article.text"
-  info usage
-  STDERR.puts usage
-  exit false 
+  usage() 
 end
 # Ω

data/lib/body.rb

@@ -146,8 +146,10 @@ class Body
   # Simple.
   def handle_uris() 
     # Determine here or elsewhere if URLs shall be verified.
-    # Default is != no. nil or '' do qualify as default.
+    # Default is no. nil or '' do qualify as default.
+    debug 'verify URLs ? ' << @@config.VFY_URLS.to_s
     if @@config.VFY_URLS
+    debug 'verifying URLs'
       @lines.each_with_index do | l, i | 
         # leave cited lines as they are.
         if !l.start_with?( '>') 

data/lib/flnews_post_proc.conf

@@ -152,9 +152,9 @@ REFERENCE_FORMAT: " ➤%s"
 #
 # If the variable is not set, a value 'yes' is assumed.
 # CONTENT: One of YES, yes, NO, no, and other variations of case.
-# DEFAULT: yes
+# DEFAULT: No
 # Example: ... I let you guess.
-VFY_URLS: YES
+VFY_URLS: No
 
 # OVERRIDE_CONFIG
 # A Boolean constant. You can choose to override the following

data/lib/flnews_post_proc.rb

@@ -54,8 +54,9 @@ class PostProcessor
     body.handle_references
     body.set_signature(newsgroups.signature)
 
-    # verify and eventually correct URLs
-    body.handle_uris
+    # verify and eventually correct URIs.
+    # ----- DANGEROUS, disabled for the time. ----
+    # body.handle_uris
 
     # get the headers and the body as a string.
     # Assemble.

data/lib/headers.rb

@@ -30,11 +30,31 @@ class Headers
     # transform the article to an array.
     debug('before split, article_text is : ' << article_text)
     line_array = article_text.split($LN)
+
+    # Emsure that all three headers are present.
+    missing_header = ['From:', 'Newsgroups:', 'Message-ID:'].detect{|h| ! line_array.any?{|l| l.match(h) } } 
+    if(missing_header)
+      msg = "Input does not look like a news-article, no #{missing_header.delete(':')}; aborting."
+      STDERR.puts msg
+      error(msg)
+      exit false
+    end
+
     debug('after split, line_array is : ' << line_array.inspect)
     # find the first empty line
     end_index = line_array.index {|ele| ele.strip == ''}
     # keep the preceding lines.
-    @lines = line_array.slice!(0, end_index)
+    begin
+      @lines = line_array.slice!(0, end_index)
+    rescue Exception => ex
+      msg = 'ERROR: cannot split the input into lines: ' << self.class.name << ': ' << ex.message
+      # console
+      STDERR.puts msg
+      # log
+      error(msg)
+      exit false
+    end
+
     debug('headers: ' << @lines.to_s)
 
     # headername: headervalue

data/lib/newsgroups.rb

@@ -109,6 +109,7 @@ class Newsgroups
             debug('signature for group(s) ' << g << ': ' << s) if sm
             if sm
               @signature = correct_linebreaks(s)
+              @signature.gsub!("\n ", "\n")
             end # if sm
           end # if no signature
         end # gsigs.each

data/lib/override.rb

@@ -40,7 +40,8 @@ class OverrideDlg
   @@LIBDIR = File::dirname(__FILE__)
   # The configuration variables that can be unset.
   # This class instance variable is exposed via a getter.
-  @cvars = [:GROUP_SIGS, :CUSTOM_HEADERS, :NO_ARCHIVE_GROUPS, :VFY_URLS, :DEBUG_LOG]
+  @cvars = [:GROUP_SIGS, :CUSTOM_HEADERS, :NO_ARCHIVE_GROUPS, :DEBUG_LOG]
+  # @cvars = [:GROUP_SIGS, :CUSTOM_HEADERS, :NO_ARCHIVE_GROUPS, :VFY_URLS, :DEBUG_LOG]
 
   # ... here
   # For the record: this is rather cool.

data/lib/ruby_dlg

@@ -50,14 +50,14 @@ if !ARGV.empty? && ARGV.length > 0
 
   opt_array = []
   message = ''
+
   menu ||= %=
   1 Unset Signature         GROUP_SIGS 
   2 Unset Custom headers    CUSTOM_HEADERS
   3 Unset No Archive        NO_ARCHIVE_GROUPS
-  4 Do not correct URLs     VFY_URLS
-  5 Disable log             DEBUG_LOG
+  4 Disable log             DEBUG_LOG
   ––––––––––––––––––––––––––––––––––––––––––––––
-  6 Summary
+  5 Summary
   ––––––––––––––––––––––––––––––––––––––––––––––
   0 Okay, use settings. 
 ––––––––––––––––––––––––––––––––––––––––––––––––
@@ -65,6 +65,21 @@ if !ARGV.empty? && ARGV.length > 0
 and no changes will be applied.
   =
 
+#  menu ||= %=
+#  1 Unset Signature         GROUP_SIGS 
+#  2 Unset Custom headers    CUSTOM_HEADERS
+#  3 Unset No Archive        NO_ARCHIVE_GROUPS
+#  4 Do not correct URLs     VFY_URLS
+#  5 Disable log             DEBUG_LOG
+#  ––––––––––––––––––––––––––––––––––––––––––––––
+#  6 Summary
+#  ––––––––––––––––––––––––––––––––––––––––––––––
+#  0 Okay, use settings. 
+#––––––––––––––––––––––––––––––––––––––––––––––––
+##{bold("Esc, Ctrl+C and 'q'")} terminate the Post-processor 
+#and no changes will be applied.
+#  =
+
   loop do
     system 'clear'
     puts yellow(menu)
@@ -111,15 +126,16 @@ and no changes will be applied.
       message = "X-No-Archive #{active ? 'removed' : 'is added'}!"
       menu.sub!("Unset X-No-Archive", "Add X-No-Archive  ") if active
       menu.sub!("Add X-No-Archive  ", "Unset X-No-Archive") if !active
+  #  when 4
+  #    active = !opt_array.include?(:VFY_URLS)
+  #    opt_array << :VFY_URLS if active
+  #    opt_array.delete(:VFY_URLS) if !active
+#
+  #    message = "URLS will #{active ? 'not ' : ''}" <<  "be verified!"
+  #    menu.sub!("Do not correct URLs", "Correct URLs       ") if active
+  #    menu.sub!("Correct URLs       ", "Do not correct URLs") if !active
+  #  when 5
     when 4
-      active = !opt_array.include?(:VFY_URLS)
-      opt_array << :VFY_URLS if active
-      opt_array.delete(:VFY_URLS) if !active
-
-      message = "URLS will #{active ? 'not ' : ''}" <<  "be verified!"
-      menu.sub!("Do not correct URLs", "Correct URLs       ") if active
-      menu.sub!("Correct URLs       ", "Do not correct URLs") if !active
-    when 5
       active = !opt_array.include?(:DEBUG_LOG)
       opt_array << :DEBUG_LOG if active
       opt_array.delete(:DEBUG_LOG) if !active
@@ -127,7 +143,8 @@ and no changes will be applied.
       message = "Log is #{ active ? 'not ' : ''} " << "written!"
       menu.sub!("Disable log", "Enable log ") if active
       menu.sub!("Enable log ", "Disable log") if !active
-    when 6
+   # when 6
+    when 5
       message = "Summary of " << bold('disabled') << " options: " << opt_array.join(' ')
     end
   end

data/lib/version.rb

@@ -14,8 +14,8 @@
 =end
 
 PROGNAME = 'flnews_post_proc'
-PROGVERSION = "1.53"
+PROGVERSION = "1.55"
 AUTHORS = "Michael Uplawski"
 EMAIL = "michael.uplawski@uplawski.eu"
 YEARS = "2023 - 2024"
-SUMMARY = "Ellipsis is replaced against '…', French documentation in sub-folder doc/fr"
+SUMMARY = "more checks on the input data, URI corrections disabled"

data/lib/whiptail_dlg

@@ -30,10 +30,12 @@ TITLE="Override post-processor configuration"
 CHECKTITLE="Deselect to disable. Esc or Cancel close the dialog and no changes will be applied."
 
 # These are the configuration variables which can be unset.
-VARS=(GROUP_SIGS CUSTOM_HEADERS NO_ARCHIVE_GROUPS VFY_URLS DEBUG_LOG)
+# VARS=(GROUP_SIGS CUSTOM_HEADERS NO_ARCHIVE_GROUPS VFY_URLS DEBUG_LOG)
+VARS=(GROUP_SIGS CUSTOM_HEADERS NO_ARCHIVE_GROUPS DEBUG_LOG)
 
 # Checklist options
-options=(GROUP_SIGS 'Signatures' ON CUSTOM_HEADERS 'Custom headers' ON NO_ARCHIVE_GROUPS 'No Archive' ON VFY_URLS 'Correct URLs' ON DEBUG_LOG 'Log' ON)
+# options=(GROUP_SIGS 'Signatures' ON CUSTOM_HEADERS 'Custom headers' ON NO_ARCHIVE_GROUPS 'No Archive' ON VFY_URLS 'Correct URLs' ON DEBUG_LOG 'Log' ON)
+options=(GROUP_SIGS 'Signatures' ON CUSTOM_HEADERS 'Custom headers' ON NO_ARCHIVE_GROUPS 'No Archive' ON DEBUG_LOG 'Log' ON)
 
 # show dialog and store results
 result=$(whiptail --title "$TITLE" --checklist "$CHECKTITLE" 13 55 5 "${options[@]}" 3>&1 1>&2 2>&3)

data/lib/yad_dlg

@@ -19,14 +19,22 @@ TITLE="Override post-processor configuration"
 GROUP_SIGS=1
 CUSTOM_HEADERS=2
 NO_ARCHIVE_GROUPS=3
-VFY_URLS=4
-DEBUG_LOG=5
+#VFY_URLS=4
+DEBUG_LOG=4
+
+#CONF=$(yad --item-separator=" " --title "$TITLE" --image="" --window-icon="" --form \
+#		--field="Uncheck to disable options\n<b>Esc and Cancel</b> terminate the post-processor.":LBL ""\
+#		--field="Signature":CHK 'true' \
+#		--field="Custom-headers":CHK 'true' \
+#		--field="No Archive":CHK 'true' \
+#		--field="URL Correction":CHK 'true' \
+#		--field="Log":CHK 'true') 
+
 CONF=$(yad --item-separator=" " --title "$TITLE" --image="" --window-icon="" --form \
 		--field="Uncheck to disable options\n<b>Esc and Cancel</b> terminate the post-processor.":LBL ""\
 		--field="Signature":CHK 'true' \
 		--field="Custom-headers":CHK 'true' \
 		--field="No Archive":CHK 'true' \
-		--field="URL Correction":CHK 'true' \
 		--field="Log":CHK 'true') 
 
 if [ $? == 0 ]

data/lib/zenity_dlg

@@ -16,14 +16,22 @@
 TITLE="Override post-processor configuration"
 # The options are the configuration variables which can be unset.
 
+#CONF=$(zenity --title "$TITLE" --text "Deselect options to disable.\n<b>Esc and Cancel</b> terminate the post-processor."\
+#        --height 450 --list --checklist --column 'set' --column 'Option' --column '' \
+#	   	TRUE GROUP_SIGS Signature\
+#	  	TRUE CUSTOM_HEADERS "Custom Headers"\
+#		TRUE NO_ARCHIVE_GROUPS "No Archive"\
+#		TRUE VFY_URLS "Correct URLs"\
+#		TRUE DEBUG_LOG Log)
+
 CONF=$(zenity --title "$TITLE" --text "Deselect options to disable.\n<b>Esc and Cancel</b> terminate the post-processor."\
         --height 450 --list --checklist --column 'set' --column 'Option' --column '' \
 	   	TRUE GROUP_SIGS Signature\
 	  	TRUE CUSTOM_HEADERS "Custom Headers"\
 		TRUE NO_ARCHIVE_GROUPS "No Archive"\
-		TRUE VFY_URLS "Correct URLs"\
 		TRUE DEBUG_LOG Log)
 
+
 if [ $? == 0 ]
 then
   IFS="|"
@@ -33,7 +41,8 @@ then
   # echo ${C_ARR[@]}
   # <-------------
 
-  for c in GROUP_SIGS CUSTOM_HEADERS NO_ARCHIVE_GROUPS VFY_URLS DEBUG_LOG
+  # for c in GROUP_SIGS CUSTOM_HEADERS NO_ARCHIVE_GROUPS VFY_URLS DEBUG_LOG
+  for c in GROUP_SIGS CUSTOM_HEADERS NO_ARCHIVE_GROUPS DEBUG_LOG
   do  
 	# disable only the options which are missing in
 	# the Zenity return value

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: flnews_post_proc
 version: !ruby/object:Gem::Version
-  version: '1.53'
+  version: '1.55'
 platform: ruby
 authors:
 - Michael Uplawski
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-06-15 00:00:00.000000000 Z
+date: 2024-07-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: diffy
@@ -30,6 +30,26 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 3.4.2
+- !ruby/object:Gem::Dependency
+  name: ruby-filemagic
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.7.3
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.7.3
 description: Post-processor for Usenet-articles created in flnews
 email: michael.uplawski@uplawski.eu
 executables:
@@ -85,5 +105,5 @@ requirements: []
 rubygems_version: 3.5.3
 signing_key:
 specification_version: 4
-summary: Ellipsis is replaced against '…', French documentation in sub-folder doc/fr
+summary: more checks on the input data, URI corrections disabled
 test_files: []