fbtxt2json 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5ef1887740ca10a869bb772542efbd1c0f96bfdfd17368e425c104f6653c497c
-  data.tar.gz: 45d1fb3ec650e499c9c0f8318dc56c942d92806d76e4a534e0ee0d541da20f5b
+  metadata.gz: 7aec08e7f51705f370e3294a721ca14985cc5f8a762dbdbafa77bdab09059417
+  data.tar.gz: d3f306984b9649b928a132d4d5261ca6c86772a9f062161f5e4612ee6b6cd0d8
 SHA512:
-  metadata.gz: af4f21b7f278fced209a80fac3c043868c64c82b5c1246da38bb56774ff34f4df06404a661ef0c449e0a62eca02dcd4e20f64826cab3011530761078f18db594
-  data.tar.gz: c1dc3ea735f2af33794c708be36bf9c6bb6ff37ae2d8cc218c61005fc923ed1775a7f7c2955c4755bc24b364020bf69924a53cacfafb6af6fa30c20b3951cd45
+  metadata.gz: 063b7d90237901bb9db1ee517c11ebfb2cac50085e24a910e25932a298ab902aafc3136bd2437bf5d57d2839c4d8f6fc9cac1de7451d0f2aca99800321e64260
+  data.tar.gz: f1c58eb56adbc74689aabd6fee371513a61f3d7dcd965f4fed13d7f6d90947004878719693e0c5a17118d496a16d059ad3ae1c28c3064f9d6f9fdc391756aaf4

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 0.3.0
+### 0.4.0
 ### 0.0.1 / 2024-09-28
 
 * Everything is new. First release.

data/Manifest.txt

@@ -4,3 +4,6 @@ README.md
 Rakefile
 bin/fbtxt2csv
 bin/fbtxt2json
+lib/fbtxt2json.rb
+lib/fbtxt2json/fbtxt2csv.rb
+lib/fbtxt2json/fbtxt2json.rb

data/README.md

@@ -1,4 +1,4 @@
-# fbtxt2json - convert football.txt match schedules & more to json
+# fbtxt2json (& fbtxt2csv) - convert football.txt match schedules & more to (structured) json or (tabular) csv
 
 
 * home  :: [github.com/sportdb/footty](https://github.com/sportdb/footty)
@@ -7,6 +7,7 @@
 * rdoc  :: [rubydoc.info/gems/fbtxt2json](http://rubydoc.info/gems/fbtxt2json)
 
 
+
 ## Step 0 - Installation Via Gems
 
 To install the command-line tool via gems (ruby's package manager) use:
@@ -27,21 +28,27 @@ $ fbtxt2json -h
 resulting in:
 
 ```
-Usage: fbtxt2json [options] PATH
+Usage: fbtxt2json [options] DATAFILES or DIRS
         --verbose, --debug           turn on verbose / debug output (default: false)
     -o, --output PATH                output to file / dir
+        --seasons SEASONS            turn on processing only seasons (default: false)
 ```
 
 
-Note - the football.txt to .json converter works in two modes. (1) you can pass in one or more files to concat(enate) into one .json output or (2) you can pass in one or more directories to convert all files (automagically) one-by-one.
+Note - the football.txt to .json converter works in two modes.
+
+(i) you can pass in one or more (match data) files to concat(enate) into one .json output or <br>
+(ii) you can pass in one or more directories to convert all (match data) files (automagically) one-by-one.
+
 
 
 
-###  Concat(enate) one or more files into one .json output
+###  Concat(enate) one or more (match data) files into one .json output
 
 Let's try to convert the "Euro" European Championship 2024
 in the Football.TXT format (see [`euro/2024--germany/euro.txt`](https://github.com/openfootball/euro/blob/master/2024--germany/euro.txt)) to JSON:
 
+
 ```
 $ fbtxt2json euro/2024--germany/euro.txt
 ```
@@ -53,7 +60,6 @@ resulting in:
   "name": "Euro 2024",
   "matches": [
     {
-      "num": 1,
       "round": "Matchday 1",
       "date": "2024-06-14", "time": "21:00",
       "team1": "Germany",
@@ -62,7 +68,6 @@ resulting in:
       "group": "Group A"
     },
     {
-      "num": 2,
       "round": "Matchday 1",
       "date": "2024-06-15", "time": "15:00",
       "team1": "Hungary",
@@ -145,9 +150,11 @@ england/
 ...
 ```
 
-Note - by default all `.txt` file extensions get changed to `.json`.
+
+Note - by default all `.txt` file extensions get changed to `.json` (if the include a season in the basename or the dirname).
 To use a different output directory use the `-o/--output` option. Example:
 
+
 ```
 $ fbtxt2json england -o ./o
 ```
@@ -174,6 +181,86 @@ That's it.
 
 
 
+
+## Bonus -  fbtxt2csv - convert football.txt (match data) files to the (tabular) comma-separated values (.csv) format
+
+
+Try in your shell / terminal:
+
+```
+$ fbtxt2csv -h
+```
+
+resulting in:
+
+```
+Usage: fbtxt2csv [options] DATAFILES and/or DIRS
+        --verbose, --debug           turn on verbose / debug output (default: false)
+    -o, --output PATH                output to file
+        --seasons SEASONS            turn on processing only seasons (default: false)
+```
+
+Let's try to convert the "Euro" European Championship 2024
+in the Football.TXT format (see [`euro/2024--germany/euro.txt`](https://github.com/openfootball/euro/blob/master/2024--germany/euro.txt)) to CSV:
+
+
+```
+$ fbtxt2csv euro/2024--germany/euro.txt -o euro2024.csv
+```
+
+resulting in:
+
+``` csv
+League,Date,Time,Team 1,Team 2,Score,HT,FT,ET,P,Round,Ground
+Euro 2024,2024-06-14,21:00,Germany,Scotland,,3-0,5-1,,,"Group A, Matchday 1",München
+Euro 2024,2024-06-15,15:00,Hungary,Switzerland,,0-2,1-3,,,"Group A, Matchday 1",Köln
+Euro 2024,2024-06-19,18:00,Germany,Hungary,,1-0,2-0,,,"Group A, Matchday 2",Stuttgart
+Euro 2024,2024-06-19,21:00,Scotland,Switzerland,,1-1,1-1,,,"Group A, Matchday 2",Köln
+Euro 2024,2024-06-23,21:00,Switzerland,Germany,,1-0,1-1,,,"Group A, Matchday 3",Frankfurt
+Euro 2024,2024-06-23,21:00,Scotland,Hungary,,0-0,0-1,,,"Group A, Matchday 3",Stuttgart
+Euro 2024,2024-06-15,18:00,Spain,Croatia,,3-0,3-0,,,"Group B, Matchday 1",Berlin
+Euro 2024,2024-06-15,21:00,Italy,Albania,,2-1,2-1,,,"Group B, Matchday 1",Dortmund
+Euro 2024,2024-06-19,15:00,Croatia,Albania,,0-1,2-2,,,"Group B, Matchday 2",Hamburg
+Euro 2024,2024-06-20,21:00,Spain,Italy,,0-0,1-0,,,"Group B, Matchday 2",Gelsenkirchen
+Euro 2024,2024-06-24,21:00,Albania,Spain,,0-1,0-1,,,"Group B, Matchday 3",Düsseldorf
+Euro 2024,2024-06-24,21:00,Croatia,Italy,,0-0,1-1,,,"Group B, Matchday 3",Leipzig
+...
+```
+
+or pass in the directory and get all (match data) files rolled-into-one tabular .csv file.
+Try:
+
+```
+$ fbtxt2csv euro -o euro.csv
+```
+
+resulting in:
+
+``` csv
+League,Date,Time,Team 1,Team 2,Score,HT,FT,ET,P,Round,Ground
+Euro 1960,1960-07-06,20:00,France,Yugoslavia,4-5,,,,,Semi-finals,"Parc des Princes, Paris"
+Euro 1960,1960-07-06,20:30,Czechoslovakia,Soviet Union,0-3,,,,,Semi-finals,"Stade Vélodrome, Marseille"
+Euro 1960,1960-07-09,21:30,Czechoslovakia,France,2-0,,,,,Third place play-off,"Stade Vélodrome, Marseille"
+Euro 1960,1960-07-10,20:30,Soviet Union,Yugoslavia,,,,2-1,,Final,"Parc des Princes, Paris"
+Euro 1964,1964-06-17,20:00,Spain,Hungary,,,,2-1,,Semi-finals,"Santiago Bernabéu, Madrid"
+Euro 1964,1964-06-17,22:30,Denmark,Soviet Union,0-3,,,,,Semi-finals,"Camp Nou, Barcelona"
+Euro 1964,1964-06-20,20:00,Hungary,Denmark,,,,3-1,,Third place play-off,"Camp Nou, Barcelona"
+Euro 1964,1964-06-21,18:30,Spain,Soviet Union,2-1,,,,,Final,"Santiago Bernabéu, Madrid"
+Euro 1968,1968-06-05,18:00,Italy,Soviet Union,,,,0-0,,Semi-finals,"Stadio San Paolo, Naples"
+Euro 1968,1968-06-05,21:15,Yugoslavia,England,1-0,,,,,Semi-finals,"Stadio Comunale, Florence"
+Euro 1968,1968-06-08,15:00,England,Soviet Union,2-0,,,,,Third place play-off,"Stadio Olimpico, Rome"
+Euro 1968,1968-06-08,21:15,Italy,Yugoslavia,,,,1-1,,Final,"Stadio Olimpico, Rome"
+Euro 1968,1968-06-10,21:15,Italy,Yugoslavia,2-0,,,,,"Final, Replay","Stadio Olimpico, Rome"
+Euro 1972,1972-06-14,20:00,West Germany,Belgium,2-1,,,,,Semi-finals,"Antwerpen, Bosuil"
+Euro 1972,1972-06-14,20:00,Soviet Union,Hungary,1-0,,,,,Semi-finals,"Brussel, Astridpark"
+Euro 1972,1972-06-17,20:00,Belgium,Hungary,2-1,,,,,Third place play-off,"Liège, Stade Sclessin"
+Euro 1972,1972-06-18,16:00,West Germany,Soviet Union,3-0,,,,,Final,"Bruxelles, Stade Heysel"
+...
+```
+
+
+
+
 ## Questions? Comments?
 
 Yes, you can. More than welcome.

data/Rakefile

@@ -2,9 +2,9 @@ require 'hoe'
 
 
 Hoe.spec 'fbtxt2json' do
-  self.version = '0.3.0'
+  self.version = '0.4.0'
 
-  self.summary = "fbtxt2json - convert football.txt match schedules & more to json"
+  self.summary = "fbtxt2json (& fbtxt2csv) - convert football.txt match schedules & more to (structured) json or (tabular) csv"
   self.description = summary
 
   self.urls = { home: 'https://github.com/sportdb/footty' }
@@ -18,10 +18,12 @@ Hoe.spec 'fbtxt2json' do
 
   self.licenses = ['Public Domain']
 
+
   self.extra_deps = [
-       ['sportdb-quick', '>= 0.2.1'],
+       ['sportdb-quick',  '>= 0.7.0'],
+       ['sportdb-parser', '>= 0.7.1'],
        ### note - include fbtok gem for (shared) command-line helpers/machinery!!!
-       ['fbtok', '>= 0.3.3'],
+       ['fbtok', '>= 0.4.1'],
   ]
 
   self.spec_extras = {

data/bin/fbtxt2csv

@@ -1,244 +1,10 @@
 #!/usr/bin/env ruby
 
-###
-#  todo/check -  move fbtxt2csv to its own top-level gem 
-##                  or add to ___ - why? why not?
-
-
 ## tip: to test run:
 ##   ruby -I ./lib bin/fbtxt2csv
 
 
-## our own code
-require 'sportdb/quick'
-
-require 'fbtok'  ### check if requires sportdb/quick  (no need to duplicate)
-
-
-
-require 'optparse'
-
-
-
-args = ARGV
-opts = {  debug:  false,
-          output: nil,
-          seasons: [],
-       }
-
-parser = OptionParser.new do |parser|
-parser.banner = "Usage: #{$PROGRAM_NAME} [options] PATH"
-
-##
-## check if git has a offline option?? (use same)
-##             check for other tools - why? why not?
-#    parser.on( "-q", "--quiet",
-#                 "less debug output/messages - default is (#{!opts[:debug]})" ) do |debug|
-#      opts[:debug] = false
-#    end
-
-   parser.on( "--verbose", "--debug",
-               "turn on verbose / debug output (default: #{opts[:debug]})" ) do |debug|
-     opts[:debug] = true
-   end
-
-   parser.on( "-o PATH", "--output PATH",
-                  "output to file" ) do |output|
-     opts[:output] = output
-   end
-
-   parser.on( "--seasons SEASONS",
-                  "turn on processing only seasons (default: #{!opts[:seasons].empty?})" ) do |seasons|
-       pp seasons
-       seasons = seasons.split( /[, ]/ )
-       seasons = seasons.map {|season| Season.parse(season) }               
-       opts[:seasons] = seasons
-   end   
-end
-parser.parse!( args )
-
-
-puts "OPTS:"
-p opts
-puts "ARGV:"
-p args
-
-
-
-paths = if args.empty?
-          ['/sports/openfootball/euro/2021--europe/euro.txt']
-        else
-          args
-        end
-
-
-if opts[:debug]
-   SportDb::QuickMatchReader.debug = true
-   SportDb::MatchParser.debug      = true
-else
-   SportDb::QuickMatchReader.debug = false
-   SportDb::MatchParser.debug      = false
-   LogUtils::Logger.root.level = :info
-end
-
-
- 
- 
-MAX_HEADERS = [
-  'League',   
-  'Date',     
-  'Time',     
-  'Team 1',     
-  'Team 2',     
-  'HT',        
-  'FT',        
-  'ET',        
-  'P',       
-  'Round',      
-  'Status',    
-]
-
-MIN_HEADERS = [   ## always keep even if all empty
-  'League',
-  'Date',
-  'Team 1',
-  'FT',
-  'Team 2'
-]
-
-
-
-def vacuum( rows, headers: MAX_HEADERS, fixed_headers: MIN_HEADERS )
-  ## check for unused columns and strip/remove
-  counter = Array.new( MAX_HEADERS.size, 0 )
-  rows.each do |row|
-     row.each_with_index do |col, idx|
-       counter[idx] += 1  unless col.nil? || col.empty?
-     end
-  end
-
-  ## pp counter
-
-  ## check empty columns
-  headers       = []
-  indices       = []
-  empty_headers = []
-  empty_indices = []
-
-  counter.each_with_index do |num, idx|
-     header = MAX_HEADERS[ idx ]
-     if num > 0 || (num == 0 && fixed_headers.include?( header ))
-       headers << header
-       indices << idx
-     else
-       empty_headers << header
-       empty_indices << idx
-     end
-  end
-
-  if empty_indices.size > 0
-    rows = rows.map do |row|
-             row_vacuumed = []
-             row.each_with_index do |col, idx|
-               ## todo/fix: use values or such??
-               row_vacuumed << col   unless empty_indices.include?( idx )
-             end
-             row_vacuumed
-         end
-    end
-
-  [rows, headers]
-end
-
- 
-
-def parse( txt )   ### check - name parse_txt or txt_to_csv or such - why? why not?
-   quick = SportDb::QuickMatchReader.new( txt )
-   matches = quick.parse
-   name    = quick.league_name   ## quick hack - get league+season via league_name
- 
-   recs = []
-
-   matches.each do |match|
-
-      ## for separator use comma (,) or pipe (|) or ???
-      round = String.new
-      ## round << "#{match.stage} | "    if match.stage
-      ## round << "#{match.group} | "    if match.group
-      round << "#{match.stage}, "    if match.stage
-      round << "#{match.group}, "    if match.group
-      round << match.round
-
-      rec = [
-            #############################
-            ## todo/fix - split league into league_name and season!!!!
-            ###############################
-            name,  ## league name
-            match.date ? match.date : '',
-            match.time ? match.time : '',
-            match.team1,
-            match.team2,
-            (match.score1i && match.score2i)   ?  "#{match.score1i}-#{match.score2i}" : '',
-            (match.score1  && match.score2)    ?  "#{match.score1}-#{match.score2}" : '', 
-            (match.score1et && match.score2et) ?  "#{match.score1et}-#{match.score2et}" : '',     
-            (match.score1p && match.score2p)   ?  "#{match.score1p}-#{match.score2p}" : '',     
-            round,
-            match.status ? match.status : '',
-       ]
-
-       ## add more attributes e.g. ground, etc.
-
-       recs << rec
-   end
-
-   puts "  #{recs.size} record(s)"
- 
-   if quick.errors?
-      puts "!! #{quick.errors.size} parse error(s):"
-      pp quick.errors
-      exit 1
-   end
-
-   recs
-end
-
-
-recs = []
-
-paths.each do |path|
-   if Dir.exist?( path )
-      puts "==> reading dir >#{path}<..."
-   
-      datafiles = SportDb::Parser::Opts._find( path, seasons: opts[:seasons] )
-      pp datafiles
-      puts "   #{datafiles.size} datafile(s)"
-      datafiles.each_with_index do |datafile,j|
-         puts "    reading file [#{j+1}/#{datafiles.size}] >#{datafile}<..."
-         txt = read_text( datafile )
-         recs += parse( txt )
-      end
-   elsif File.exist?( path )
-      puts "==> reading file >#{path}<..."
-      txt = read_text( path )
-      recs += parse( txt )
-   else ## not a file or dir repprt errr
-       raise ArgumentError, "file/dir does NOT exist - #{path}"
-   end
-end
-
-
-recs, headers = vacuum( recs )
-pp recs[0,10]   ## dump first 10 records
-pp headers
-puts "  #{recs.size} record(s)"
-
-
-if opts[:output]
-   puts "==> writing matches to #{opts[:output]}"
-   write_csv( opts[:output], recs,
-              headers: headers )
-end
-
+require 'fbtxt2json'
 
-puts "bye"
 
+Fbtxt2csv.main

data/bin/fbtxt2json

@@ -1,219 +1,10 @@
 #!/usr/bin/env ruby
 
 ## tip: to test run:
-##   ruby -I ./lib bin/fbtxt2json
+##   $ ruby -I ./lib bin/fbtxt2json
 
 
-#####
-## todo
-##   add option for [no]-halt-on-error (default: false)
-##      or use a different (shorter) name e.g. --resume?
+require 'fbtxt2json'
 
 
-
-## our own code
-require 'sportdb/quick'
-
-require 'fbtok'  ### check if requires sportdb/quick  (no need to duplicate)
-
-
-
-require 'optparse'
-
-
-
-args = ARGV
-opts = {  debug:  false,
-          output: nil,
-          summary: false,
-          seasons: [],
-       }
-
-parser = OptionParser.new do |parser|
-parser.banner = "Usage: #{$PROGRAM_NAME} [options] PATH"
-
-##
-## check if git has a offline option?? (use same)
-##             check for other tools - why? why not?
-#    parser.on( "-q", "--quiet",
-#                 "less debug output/messages - default is (#{!opts[:debug]})" ) do |debug|
-#      opts[:debug] = false
-#    end
-
-   parser.on( "--verbose", "--debug",
-               "turn on verbose / debug output (default: #{opts[:debug]})" ) do |debug|
-     opts[:debug] = true
-   end
-
-   parser.on( "-o PATH", "--output PATH",
-                  "output to file / dir" ) do |output|
-     opts[:output] = output
-   end
-
-   parser.on( "--summary", 
-                  "(auto-)generate summary (index.html) page (default: #{opts[:summary]})" ) do |summary|
-     opts[:summary] = summary
-   end
-
-   parser.on( "--seasons SEASONS",
-                  "turn on processing only seasons (default: #{!opts[:seasons].empty?})" ) do |seasons|
-       pp seasons
-       seasons = seasons.split( /[, ]/ )
-       seasons = seasons.map {|season| Season.parse(season) }               
-       opts[:seasons] = seasons
-   end   
-end
-parser.parse!( args )
-
-
-puts "OPTS:"
-p opts
-puts "ARGV:"
-p args
-
-
-
-paths = if args.empty?
-          ['/sports/openfootball/euro/2021--europe/euro.txt']
-        else
-          args
-        end
-
-
-if opts[:debug]
-   SportDb::QuickMatchReader.debug = true
-   SportDb::MatchParser.debug      = true
-else
-   SportDb::QuickMatchReader.debug = false
-   SportDb::MatchParser.debug      = false
-   LogUtils::Logger.root.level = :info
-end
-
-
-###
-##  two modes -   process directories or  concat(enate)d files 
-##
-##   check if args is a directory
-##
-dirs  = 0
-files = 0
-paths.each do |path|
-     if Dir.exist?( path )
-        dirs  += 1
-     elsif File.exist?( path )
-        files += 1
-     else ## not a file or dir repprt errr
-         raise ArgumentError, "file/dir does NOT exist - #{path}"
-     end
-end
-
-if dirs > 0 && files > 0
-     raise ArgumentError, "#{files} file(s), #{dirs} dir(s) - can only process dirs or files but NOT both; sorry"
-end
-
-
-
-def parse( txt,
-            summary: nil, 
-            dump: false )   ### check - name parse_txt or txt_to_json or such - why? why not?
-   quick = SportDb::QuickMatchReader.new( txt )
-   matches = quick.parse
-   name    = quick.league_name   ## quick hack - get league+season via league_name
- 
-   data = { 'name'    => name,
-            'matches' => matches.map {|match| match.as_json }}
-  
-   if dump
-     pp data
-     puts
-   end
-   puts "  #{matches.size} match(es)"
- 
-   if quick.errors?
-      puts "!! #{quick.errors.size} parse error(s):"
-      pp quick.errors
-      exit 1
-   end
-
-
-   if summary
-      ## add stats to summary page
-      summary << "- #{name} | #{matches.size} match(es)\n"
-   end
-
-   data
-end
-
-
-if files > 0
-  ## step 1 - concat(enate) all text files into one
-  txt = String.new
-  paths.each_with_index do |path,i|
-    puts "==> reading file [#{i+1}/#{paths.size}] >#{path}<..."
-    txt += "\n\n"   if i > 0
-    txt += read_text( path )
-  end
-
-  ## step 2 - parse (matches) in the football.txt format
-  data = parse( txt, dump: true )
- 
-  if opts[:output]
-     puts "==> writing matches to #{opts[:output]}"
-     write_json( opts[:output], data )
-  end
-elsif dirs > 0
-
-   ## use a html pre(formatted) text
-   summary = String.new
-   summary << "<pre>\n"
-   summary << "run on #{Time.now.to_s}\n\n"   ## add version and such - why? why not?
-
-   paths.each_with_index do |path,i|
-      puts "==> reading dir [#{i+1}/#{paths.size}] >#{path}<..."
-      summary << "==> [#{i+1}/#{paths.size}] dir #{path}\n"
-
-
-      datafiles = SportDb::Parser::Opts._find( path, seasons: opts[:seasons] )
-      pp datafiles
-      puts "   #{datafiles.size} datafile(s)"
-      summary << "    #{datafiles.size} datafile(s)\n\n"
-
-      datafiles.each do |datafile|
-         txt = read_text( datafile )
-         data = parse( txt, summary: summary )
-
-         if opts[:output]
-            ### norm - File.expand_path !!!
-            ##   note - use '.' to use (relative to) local directory !!!
-            reldir = File.expand_path(File.dirname( path ))   ## keep last dir (in relative name)
-            relpath = datafile.sub( reldir+'/', '' )
-            dir     = File.dirname( relpath )
-            ## puts "  reldir = #{reldir}, datafile = #{datafile}"
-            ## puts "  relpath = #{relpath}, dir = #{dir}"
-            basename = File.basename( relpath, File.extname(relpath)) 
-            outpath  = "#{opts[:output]}/#{dir}/#{basename}.json"
-         else
-           dir = File.dirname( datafile )  
-           basename = File.basename( datafile, File.extname(datafile) ) 
-           outpath = "#{dir}/#{basename}.json"
-         end
-         puts "  writing matches to #{outpath}"
-         write_json( outpath, data )
-      end
-   end
-
-   summary << "</pre>"
-   puts summary
-   ## note - do NOT write-out summary if seasons filter is used!!!
-   if opts[:summary] && opts[:seasons].size == 0
-     write_text( "#{opts[:output]}/index.html", summary )
-   end
-else 
-   ## do nothing; no args
-end
-
-
-
-
-puts "bye"
-
+Fbtxt2json.main

data/lib/fbtxt2json/fbtxt2csv.rb

@@ -0,0 +1,250 @@
+
+module Fbtxt2csv
+
+
+def self.main( args=ARGV )
+
+
+
+opts = {  debug:  false,
+          output: nil,
+          seasons: [],
+       }
+
+parser = OptionParser.new do |parser|
+parser.banner = "Usage: #{$PROGRAM_NAME} [options] DATAFILES and/or DIRS"
+
+##
+## check if git has a offline option?? (use same)
+##             check for other tools - why? why not?
+#    parser.on( "-q", "--quiet",
+#                 "less debug output/messages - default is (#{!opts[:debug]})" ) do |debug|
+#      opts[:debug] = false
+#    end
+
+   parser.on( "--verbose", "--debug",
+               "turn on verbose / debug output (default: #{opts[:debug]})" ) do |debug|
+     opts[:debug] = true
+   end
+
+   parser.on( "-o PATH", "--output PATH",
+                  "output to file" ) do |output|
+     opts[:output] = output
+   end
+
+   parser.on( "--seasons SEASONS",
+                  "turn on processing only seasons (default: #{!opts[:seasons].empty?})" ) do |seasons|
+       pp seasons
+       seasons = seasons.split( /[, ]/ )
+       seasons = seasons.map {|season| Season.parse(season) }
+       opts[:seasons] = seasons
+   end
+end
+parser.parse!( args )
+
+
+puts "OPTS:"
+p opts
+puts "ARGV:"
+p args
+
+
+
+paths = if args.empty?
+          ['/sports/openfootball/euro/2021--europe/euro.txt']
+        else
+          args
+        end
+
+
+if opts[:debug]
+   SportDb::QuickMatchReader.debug = true
+   SportDb::MatchParser.debug      = true
+else
+   SportDb::QuickMatchReader.debug = false
+   SportDb::MatchParser.debug      = false
+   LogUtils::Logger.root.level = :info
+end
+
+
+
+recs = []
+
+paths.each do |path|
+   if Dir.exist?( path )
+      puts "==> reading dir >#{path}<..."
+
+      datafiles = SportDb::Pathspec._find( path, seasons: opts[:seasons] )
+      pp datafiles
+      puts "   #{datafiles.size} datafile(s)"
+      datafiles.each_with_index do |datafile,j|
+         puts "    reading file [#{j+1}/#{datafiles.size}] >#{datafile}<..."
+         txt = read_text( datafile )
+         recs += parse( txt )
+      end
+   elsif File.file?( path )    ## note - File.exist? also incl. Dir - use anyway - why? why not?
+      puts "==> reading file >#{path}<..."
+      txt = read_text( path )
+      recs += parse( txt )
+   else ## not a file or dir report error
+       raise ArgumentError, "file/dir does NOT exist - #{path}"
+   end
+end
+
+
+recs, headers = vacuum( recs )
+pp recs[0,2]   ## dump first 2 records
+pp headers
+puts "  #{recs.size} record(s)"
+
+
+if opts[:output]
+   puts "==> writing matches to #{opts[:output]}"
+   write_csv( opts[:output], recs,
+              headers: headers )
+end
+
+
+puts "bye"
+end  # self.main
+
+
+
+
+MAX_HEADERS = [
+  'League',
+  'Date',
+  'Time',
+  'Team 1',
+  'Team 2',
+  'Score',      ## generic score - do NOT know if FT/ET or such
+  'HT',
+  'FT',
+  'ET',
+  'P',
+  'Round',
+  'Status',
+  'Ground',
+]
+
+
+MIN_HEADERS = [   ## always keep even if all empty
+  'League',
+  'Date',
+  'Team 1',
+  'Team 2'
+]
+
+
+
+def self.vacuum( rows, headers: MAX_HEADERS, fixed_headers: MIN_HEADERS )
+  ## check for unused columns and strip/remove
+  counter = Array.new( MAX_HEADERS.size, 0 )
+  rows.each do |row|
+     row.each_with_index do |col, idx|
+       counter[idx] += 1  unless col.nil? || col.empty?
+     end
+  end
+
+  ## pp counter
+
+  ## check empty columns
+  headers       = []
+  indices       = []
+  empty_headers = []
+  empty_indices = []
+
+  counter.each_with_index do |num, idx|
+     header = MAX_HEADERS[ idx ]
+     if num > 0 || (num == 0 && fixed_headers.include?( header ))
+       headers << header
+       indices << idx
+     else
+       empty_headers << header
+       empty_indices << idx
+     end
+  end
+
+  if empty_indices.size > 0
+    rows = rows.map do |row|
+             row_vacuumed = []
+             row.each_with_index do |col, idx|
+               ## todo/fix: use values or such??
+               row_vacuumed << col   unless empty_indices.include?( idx )
+             end
+             row_vacuumed
+         end
+    end
+
+  [rows, headers]
+end
+
+
+
+def self.parse( txt )   ### check - name parse_txt or txt_to_csv or such - why? why not?
+   quick = SportDb::QuickMatchReader.new( txt )
+   matches = quick.parse
+   name    = quick.league_name   ## quick hack - get league+season via league_name
+
+   recs = []
+
+
+   matches.each do |match|
+      ## pp match
+      ## pp match.status
+      ## pp match.round
+      ## pp match.score
+      ## pp match.score
+
+      round = String.new
+      round << "#{match.group}, "    if match.group
+      round << match.round           if match.round
+
+      ## note - make.score hash uses symbols!!!
+      ##         e.g. score[:ht] and NOT score['ht'] !!!
+      #    make sure hash keys are always strings
+      score = match.score
+      score = score.transform_keys(&:to_s)   if score.is_a?( Hash )
+
+      ground =   if match.ground.is_a?( Array )
+                     match.ground.join(', ')
+                 else  ## assume string or nil
+                     match.ground ? match.ground : ''
+                 end
+
+      rec = [
+            #############################
+            ## todo/fix - split league into league_name and season!!!!
+            ###############################
+            name,  ## league name
+            match.date ? match.date : '',
+            match.time ? match.time : '',
+            match.team1,
+            match.team2,
+            score.is_a?( Array ) && score.size == 2 ?  "#{score[0]}-#{score[1]}" : '',
+            score.is_a?( Hash ) && score['ht'] ?  "#{score['ht'][0]}-#{score['ht'][1]}" : '',
+            score.is_a?( Hash ) && score['ft'] ?  "#{score['ft'][0]}-#{score['ft'][1]}" : '',
+            score.is_a?( Hash ) && score['et'] ?  "#{score['et'][0]}-#{score['et'][1]}" : '',
+            score.is_a?( Hash ) && score['p']  ?  "#{score['p'][0]}-#{score['p'][1]}" : '',
+            round,
+            match.status ? match.status : '',
+            ground,
+       ]
+
+       ## add more attributes e.g. ground, etc.
+
+       recs << rec
+   end
+
+   puts "  #{recs.size} record(s)"
+
+   if quick.errors?
+      puts "!! #{quick.errors.size} parse error(s):"
+      pp quick.errors
+      exit 1
+   end
+
+   recs
+end   # self.parse
+
+end # module Fbtxt2csv

data/lib/fbtxt2json/fbtxt2json.rb

@@ -0,0 +1,229 @@
+#####
+## todo
+##   add option for [no]-halt-on-error (default: false)
+##      or use a different (shorter) name e.g. --resume?
+
+
+module Fbtxt2json
+
+
+def self.main( args=ARGV )
+
+opts = {  debug:   false,
+          output:  nil,
+          summary: false,
+          seasons: [],
+       }
+
+
+parser = OptionParser.new do |parser|
+parser.banner = "Usage: #{$PROGRAM_NAME} [options] DATAFILES or DIRS"
+
+##
+## check if git has a offline option?? (use same)
+##             check for other tools - why? why not?
+#    parser.on( "-q", "--quiet",
+#                 "less debug output/messages - default is (#{!opts[:debug]})" ) do |debug|
+#      opts[:debug] = false
+#    end
+
+   parser.on( "--verbose", "--debug",
+               "turn on verbose / debug output (default: #{opts[:debug]})" ) do |debug|
+     opts[:debug] = true
+   end
+
+   parser.on( "-o PATH", "--output PATH",
+                  "output to file / dir" ) do |output|
+     opts[:output] = output
+   end
+
+   parser.on( "--summary",
+                  "(auto-)generate summary (index.html) page (default: #{opts[:summary]})" ) do |summary|
+     opts[:summary] = summary
+   end
+
+   parser.on( "--seasons SEASONS",
+                  "turn on processing only seasons (default: #{!opts[:seasons].empty?})" ) do |seasons|
+       pp seasons
+       seasons = seasons.split( /[, ]/ )
+       seasons = seasons.map {|season| Season.parse(season) }
+       opts[:seasons] = seasons
+   end
+end
+parser.parse!( args )
+
+
+puts "OPTS:"
+p opts
+puts "ARGV:"
+p args
+
+
+
+paths = if args.empty?
+          ['/sports/openfootball/euro/2021--europe/euro.txt']
+        else
+          args
+        end
+
+
+if opts[:debug]
+   SportDb::QuickMatchReader.debug = true
+   SportDb::MatchParser.debug      = true
+else
+   SportDb::QuickMatchReader.debug = false
+   SportDb::MatchParser.debug      = false
+   LogUtils::Logger.root.level = :info
+end
+
+
+###
+##  two modes -   process directories or  concat(enate)d files
+##
+##   check if args is a directory
+##
+dirs  = 0
+files = 0
+paths.each do |path|
+     if Dir.exist?( path )
+        dirs  += 1
+     elsif File.file?( path )   ## note - strictly File.exist? also checks for dirs (use File.file?)!!
+        files += 1
+     else ## not a file or dir repprt errr
+         raise ArgumentError, "file/dir does NOT exist - #{path}"
+     end
+end
+
+if dirs > 0 && files > 0
+     raise ArgumentError, "#{files} file(s), #{dirs} dir(s) - can only process dirs or files but NOT both; sorry"
+end
+
+
+
+
+if files > 0
+    do_files( paths, outpath: opts[:output]  )
+elsif dirs > 0
+    do_dirs( paths, outdir:        opts[:output],
+                    seasons:       opts[:seasons],
+                    write_summary: opts[:summary] )
+else
+   ## do nothing; no args
+end
+
+
+puts "bye"
+end # self.main
+
+
+
+def self.do_files( paths, outpath: nil )
+    data = nil
+    paths.each_with_index do |path,i|
+      puts "==> reading file [#{i+1}/#{paths.size}] >#{path}<..."
+      txt = read_text( path )
+      more_data = parse( txt )
+
+      if data.nil?
+         data = more_data
+      else
+          ## concat matches
+          ##  check if name match up!!!
+          if data['name'] != more_data['name']
+             raise ArgumentError, "cannot merge matchfiles - league names do NOT match: #{data['name']} != #{more_data['name']}"
+          else
+              data['matches'] += more_data['matches']
+          end
+      end
+    end
+
+     pp data
+     puts
+     puts "  #{data['matches'].size} match(es)"
+
+    if outpath
+       puts "==> writing matches to #{outpath}"
+       write_json( outpath, data )
+    end
+end
+
+
+
+def self.do_dirs( paths, outdir: nil,
+                         seasons: [],
+                         write_summary: false )
+
+   ## use a html pre(formatted) text
+   summary = String.new
+   summary << "<pre>\n"
+   summary << "run on #{Time.now.to_s}\n\n"   ## add version and such - why? why not?
+
+
+   paths.each_with_index do |path,i|
+      puts "==> reading dir [#{i+1}/#{paths.size}] >#{path}<..."
+      summary << "==> [#{i+1}/#{paths.size}] dir #{path}\n"
+
+      datafiles = SportDb::Pathspec._find( path, seasons: seasons )
+      pp datafiles
+      puts "   #{datafiles.size} datafile(s)"
+      summary << "    #{datafiles.size} datafile(s)\n\n"
+
+      datafiles.each do |datafile|
+         txt = read_text( datafile )
+         data = parse( txt )
+
+         ## add stats to summary page
+         summary << "- #{data['name']} | #{data['matches'].size} match(es) - #{datafile}\n"
+
+
+         if outdir
+            ### norm - File.expand_path !!!
+            ##   note - use '.' to use (relative to) local directory !!!
+            reldir = File.expand_path(File.dirname( path ))   ## keep last dir (in relative name)
+            relpath = datafile.sub( reldir+'/', '' )
+            dir     = File.dirname( relpath )
+            ## puts "  reldir = #{reldir}, datafile = #{datafile}"
+            ## puts "  relpath = #{relpath}, dir = #{dir}"
+            basename = File.basename( relpath, File.extname(relpath))
+            outpath  = "#{outdir}/#{dir}/#{basename}.json"
+         else
+           dir = File.dirname( datafile )
+           basename = File.basename( datafile, File.extname(datafile) )
+           outpath = "#{dir}/#{basename}.json"
+         end
+         puts "  writing matches to #{outpath}"
+         write_json( outpath, data )
+      end
+   end
+
+   summary << "</pre>"
+   puts summary
+
+   ## note - do NOT write-out summary if seasons filter is used!!!
+   if outdir && write_summary && seasons.empty?
+     write_text( "#{outdir}/index.html", summary )
+   end
+end
+
+
+
+def self.parse( txt )   ### check - name parse_txt or txt_to_json or such - why? why not?
+   quick = SportDb::QuickMatchReader.new( txt )
+   matches = quick.parse
+   name    = quick.league_name   ## quick hack - get league+season via league_name
+
+   data = { 'name'    => name,
+            'matches' => matches.map {|match| match.as_json }}
+
+
+   if quick.errors?
+      puts "!! #{quick.errors.size} parse error(s):"
+      pp quick.errors
+      exit 1
+   end
+
+   data
+end
+
+
+end # module Fbtxt2json

data/lib/fbtxt2json.rb

@@ -0,0 +1,10 @@
+
+require 'sportdb/quick'
+
+require 'fbtok'  ### check if requires sportdb/quick  (no need to duplicate)
+
+
+
+## our own code
+require_relative 'fbtxt2json/fbtxt2json'
+require_relative 'fbtxt2json/fbtxt2csv'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: fbtxt2json
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-04-08 00:00:00.000000000 Z
+date: 2026-05-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: sportdb-quick
@@ -16,28 +16,42 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.1
+        version: 0.7.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.1
+        version: 0.7.0
+- !ruby/object:Gem::Dependency
+  name: sportdb-parser
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.7.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.7.1
 - !ruby/object:Gem::Dependency
   name: fbtok
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.3.3
+        version: 0.4.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.3.3
+        version: 0.4.1
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
@@ -72,7 +86,8 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '4.2'
-description: fbtxt2json - convert football.txt match schedules & more to json
+description: fbtxt2json (& fbtxt2csv) - convert football.txt match schedules & more
+  to (structured) json or (tabular) csv
 email: gerald.bauer@gmail.com
 executables:
 - fbtxt2csv
@@ -89,6 +104,9 @@ files:
 - Rakefile
 - bin/fbtxt2csv
 - bin/fbtxt2json
+- lib/fbtxt2json.rb
+- lib/fbtxt2json/fbtxt2csv.rb
+- lib/fbtxt2json/fbtxt2json.rb
 homepage: https://github.com/sportdb/footty
 licenses:
 - Public Domain
@@ -113,5 +131,6 @@ requirements: []
 rubygems_version: 3.5.22
 signing_key:
 specification_version: 4
-summary: fbtxt2json - convert football.txt match schedules & more to json
+summary: fbtxt2json (& fbtxt2csv) - convert football.txt match schedules & more to
+  (structured) json or (tabular) csv
 test_files: []