csvutils 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 91b99040998dec29903bb139c7650aec805981c9
-  data.tar.gz: 4ca0a379e0a99dc01f35957ca021ccb4b56aaef3
+  metadata.gz: 435468b42345511466981b9f470e39e1dc78bfea
+  data.tar.gz: f2b4c42ec30da76fe929942d6d0706420dd63f63
 SHA512:
-  metadata.gz: 7cae580d42247f3df41c846880cdfc78f4f410fc553acff75b57cf85d542a80e97c6ef4ec7e1e924b1cdd85934596addc4d0941bdab9e31478bf0e012386eaf2
-  data.tar.gz: 8398dabd6e1bf01134ba31016b77a866c308c7a75ef426b1ebc995d043c11ec757c15c07bc5b8ba2f81764fa796ad96013055b19af30b70504647aff3915b570
+  metadata.gz: 1b1edc99a8b3e7257a899df34ed2b144467c1268f21877676194b138e59113d69733990ba7a0c70b1a4c51cb2861dff6e3c429cbc9f6be4a0a83c9f08a52fd22
+  data.tar.gz: b57408a1a5d2743649538c79a269480ce2a20d21df483c8133772bbb46589d7dbff6d1c9b22d4ec329bf331f70bd5a207650bedfd83821ba2cdeb7787595621b

data/Manifest.txt

@@ -4,7 +4,10 @@ README.md
 Rakefile
 lib/csvutils.rb
 lib/csvutils/cut.rb
+lib/csvutils/head.rb
+lib/csvutils/header.rb
 lib/csvutils/split.rb
+lib/csvutils/stat.rb
 lib/csvutils/test.rb
 lib/csvutils/utils.rb
 lib/csvutils/version.rb

data/README.md

@@ -1,4 +1,4 @@
-# csvutils - tools 'n' scripts for working with comma-separated values (csv) datafiles - the world's most popular tabular date interchange format in text"
+# csvutils - tools 'n' scripts for working with comma-separated values (csv) datafiles - the world's most popular tabular date interchange format in text
 
 
 * home  :: [github.com/csv11/csvutils](https://github.com/csv11/csvutils)

data/Rakefile

@@ -11,7 +11,7 @@ Hoe.spec 'csvutils' do
   self.urls = ['https://github.com/csv11/csvutils']
 
   self.author = 'Gerald Bauer'
-  self.email = 'opensport@googlegroups.com'
+  self.email = 'wwwmake@googlegroups.com'
 
   # switch extension to .markdown for gihub formatting
   self.readme_file = 'README.md'

data/lib/csvutils.rb

@@ -4,6 +4,8 @@ require 'pp'
 require 'csv'
 require 'date'
 require 'fileutils'
+require 'optparse'
+
 
 
 ###
@@ -13,7 +15,114 @@ require 'csvutils/utils'
 require 'csvutils/split'
 require 'csvutils/cut'
 require 'csvutils/test'
+require 'csvutils/stat'
+require 'csvutils/header'
+require 'csvutils/head'
+
+
+
+
+class CsvTool
+
+## command line tools
+def self.header( args )
+
+  config = {}
+
+  parser = OptionParser.new do |opts|
+     opts.banner = "Usage: csvheader [OPTS] datafile ..."
+
+     opts.on("-h", "--help", "Prints this help") do
+       puts opts
+       exit
+     end
+  end
+
+  parser.parse!( args )
+
+  ## pp config
+  ## pp args
+
+  args.each do |arg|
+    path = arg
+
+    puts "== #{File.basename(path)} (#{File.dirname(path)}) =="
+    puts
+    CsvUtils.pp_header( CsvUtils.header( path ) )
+    puts
+  end # each arg
+end
+
+
+def self.stat( args )
+
+  config = { columns: [] }
+
+  parser = OptionParser.new do |opts|
+     opts.banner = "Usage: csvstat [OPTS] datafile ..."
+
+     opts.on("-c", "--columns=COLUMNS", "Name of header columns" ) do |columns|
+       config[:columns] = columns.split(/[,|;]/)   ## allow differnt separators
+     end
+
+     opts.on("-h", "--help", "Prints this help") do
+       puts opts
+       exit
+     end
+  end
+
+  parser.parse!( args )
+
+  ## pp config
+  ## pp args
+
+  args.each do |arg|
+    path = arg
+    columns = config[:columns]
+
+    puts "== #{File.basename(path)} (#{File.dirname(path)}) =="
+    puts
+    CsvUtils.stat( path, *columns )
+    puts
+  end # each arg
+end
+
+
+def self.head( args )
+
+  config = { n: 4 }
+
+  parser = OptionParser.new do |opts|
+     opts.banner = "Usage: csvhead [OPTS] datafile ..."
+
+     opts.on("-n", "--num=NUM", "Number of rows" ) do |num|
+       config[:n] = num.to_i
+     end
+
+     opts.on("-h", "--help", "Prints this help") do
+       puts opts
+       exit
+     end
+  end
+
+  parser.parse!( args )
+
+  ## pp config
+  ## pp args
+
+  args.each do |arg|
+    path = arg
+    n = config[:n]
+
+    puts "== #{File.basename(path)} (#{File.dirname(path)}) =="
+    puts
+    CsvUtils.head( path, n: n )
+    puts
+  end # each arg
+end
+
 
+end # class CsvTool
 
 
 puts CsvUtils.banner   # say hello

data/lib/csvutils/cut.rb

@@ -1,47 +1,47 @@
-# encoding: utf-8
-
-## check/use class or module ???
-
-
-class CsvUtils
-
-  def self.cut( inpath, outpath, *columns, sep: ',' )
-
-    puts "cvscut in: >#{inpath}<  out: >#{outpath}<"
-
-    ##  ["Date", "HomeTeam", "AwayTeam", "FTHG", "FTAG", "HTHG", "HTAG"]
-    puts "columns:"
-    pp columns
-
-    text = File.open( inpath, 'r:utf-8' ).read   ## note: make sure to use (assume) utf-8
-
-    csv_options = { headers: true,
-                    col_sep: sep }
-
-    table = CSV.parse( text, csv_options )
-
-
-    ## for convenience - make sure parent folders/directories exist
-    FileUtils.mkdir_p( File.dirname( outpath ))  unless Dir.exists?( File.dirname( outpath ))
-
-    ## use wb mode - why? why not?
-    ##   assumes same encoding as input?
-    ##   fix/todo: better (always) use utf8!!!!
-    ## CSV.open( out_path, 'wb' ) do |out|
-
-    ## use just "regular" File for output - why? why not?
-    ##    downside will not encode comma (for now) if present ("Beethoven, van")
-    ##      all values will be unquoted etc. - keep it simple?
-
-    CSV.open( outpath, 'w:utf-8' ) do |out|
-      out << columns   ## for row add headers/columns
-      table.each do |row|
-        values = columns.map { |col| row[col].strip }  ## find data for column
-        out << values
-      end
-    end
-
-    puts 'Done.'
-  end  ## method self.cut
-
-end # class CsvUtils
+# encoding: utf-8
+
+## check/use class or module ???
+
+
+class CsvUtils
+
+  def self.cut( inpath, outpath, *columns, sep: ',' )
+
+    puts "cvscut in: >#{inpath}<  out: >#{outpath}<"
+
+    ##  ["Date", "HomeTeam", "AwayTeam", "FTHG", "FTAG", "HTHG", "HTAG"]
+    puts "columns:"
+    pp columns
+
+    text = File.open( inpath, 'r:utf-8' ).read   ## note: make sure to use (assume) utf-8
+
+    csv_options = { headers: true,
+                    col_sep: sep }
+
+    table = CSV.parse( text, csv_options )
+
+
+    ## for convenience - make sure parent folders/directories exist
+    FileUtils.mkdir_p( File.dirname( outpath ))  unless Dir.exists?( File.dirname( outpath ))
+
+    ## use wb mode - why? why not?
+    ##   assumes same encoding as input?
+    ##   fix/todo: better (always) use utf8!!!!
+    ## CSV.open( out_path, 'wb' ) do |out|
+
+    ## use just "regular" File for output - why? why not?
+    ##    downside will not encode comma (for now) if present ("Beethoven, van")
+    ##      all values will be unquoted etc. - keep it simple?
+
+    CSV.open( outpath, 'w:utf-8' ) do |out|
+      out << columns   ## for row add headers/columns
+      table.each do |row|
+        values = columns.map { |col| row[col].strip }  ## find data for column
+        out << values
+      end
+    end
+
+    puts 'Done.'
+  end  ## method self.cut
+
+end # class CsvUtils

data/lib/csvutils/head.rb

@@ -0,0 +1,25 @@
+# encoding: utf-8
+
+
+class CsvUtils
+
+  ## test or dry run to check if rows can get read/scanned
+  def self.head( path, sep: ',', n: 4 )
+    i = 0
+    csv_options = { headers: true,
+                    col_sep: sep,
+                    external_encoding: 'utf-8'  ## note:  always (auto-)add utf-8 external encoding!!!
+                   }
+
+    CSV.foreach( path, csv_options ) do |row|
+      i += 1
+
+      pp row
+
+      break if i >= n
+    end
+
+    puts " #{i} rows"
+  end
+
+end  # class CsvUtils

data/lib/csvutils/header.rb

@@ -0,0 +1,28 @@
+# encoding: utf-8
+
+
+class CsvUtils
+
+  def self.header( path, sep: ',', debug: false )   ## use header or headers - or use both (with alias)?
+
+    # read first line (only)
+    #  and parse with csv to get header from csv library itself
+    #
+    #  check - if there's an easier or built-in way for the csv library
+
+    line = File.open( path, 'r:utf-8' ) { |f| f.readline }
+
+    pp line   if debug
+    ## e.g.:
+    #  "Country,League,Season,Date,Time,Home,Away,HG,AG,Res,PH,PD,PA,MaxH,MaxD,MaxA,AvgH,AvgD,AvgA\n"
+
+    csv_options = {  col_sep: sep }
+
+    ## note: do NOT use headers: true to get "plain" data array (no hash records)
+    ##   hash record does NOT work for single line/row
+    rows = CSV.parse( line, csv_options )
+    pp rows   if debug
+    rows[0]   ## return first row
+  end  # method self.header
+
+end  # class CsvUtils

data/lib/csvutils/split.rb

@@ -1,107 +1,107 @@
-# encoding: utf-8
-
-
-
-
-class CsvUtils
-
-  def self.split( path, *columns, sep: ',', &blk )
-
-    puts "cvssplit in: >#{path}<"
-
-    ##  ["Date", "HomeTeam", "AwayTeam", "FTHG", "FTAG", "HTHG", "HTAG"]
-    puts "columns:"
-    pp columns
-
-    text = File.open( path, 'r:utf-8' ).read   ## note: make sure to use (assume) utf-8
-
-    ## note: do NOT use headers
-    ##   for easy sorting use "plain" array of array for records
-    csv_options = { col_sep: sep }
-
-    data = CSV.parse( text, csv_options )
-
-    ## todo/check: (auto-) strip (remove all leading and trailing spaces)
-    ##     from all values - why? why not?
-    ##   check if CSV.parse has an option for it?
-
-    headers = data.shift   ## remove top array item (that is, row with headers)
-
-    header_mapping = {}
-    headers.each_with_index  { | header,i | header_mapping[header]=i }
-    pp header_mapping
-
-    ## map columns to array indices e.g. ['Season', 'Div'] => [1,2]
-    column_indices = columns.map { |col| header_mapping[col] }
-    pp column_indices
-
-
-    ###################################################
-    ## note: sort data by columns (before split)
-    data = data.sort do |row1,row2|
-       res = 0
-       column_indices.each do |col|
-         res = row1[col] <=> row2[col]    if res == 0
-       end
-       res
-    end
-
-    chunk = []
-    data.each_with_index do |row,i|
-      chunk << row
-
-      next_row = data[i+1]
-
-      changed = false
-      if next_row.nil?   ## end-of-file
-        changed = true
-      else
-        column_indices.each do |col|
-          if row[col] != next_row[col]
-             changed = true
-             break   ## out of each column_indices loop
-           end
-        end
-      end
-
-      if changed
-        puts "save new chunk:"
-        column_values = column_indices.map {|col| row[col] }
-        pp column_values
-
-        # note: add header(s) row upfront (as first row) to chunk (with unshift)
-        chunk_with_headers = chunk.unshift( headers )
-        if blk
-          yield( column_values, chunk_with_headers )
-        else
-          ## auto-save (write-to-file) by default - why? why not?
-          split_write( path, column_values, chunk_with_headers )
-        end
-
-        chunk = []   ## reset chunk for next batch of records
-      end
-    end
-
-    puts 'Done.'
-  end  ## method self.split
-
-
-  def self.split_write( inpath, values, chunk )
-    basename = File.basename( inpath, '.*' )
-    dirname  = File.dirname( inpath )
-
-    ## check/change invalid filename chars
-    ##  e.g. change 1990/91 to 1990-91
-    extraname = values.map {|value| value.tr('/','-')}.join('~')
-
-    outpath = "#{dirname}/#{basename}_#{extraname}.csv"
-    puts "saving >#{basename}_#{extraname}.csv<..."
-
-    CSV.open( outpath, 'w:utf-8' ) do |out|
-      chunk.each do |row|
-        out << row
-      end
-    end
-  end
-
-end # class CsvUtils
+# encoding: utf-8
+
+
+
+
+class CsvUtils
+
+  def self.split( path, *columns, sep: ',', &blk )
+
+    puts "cvssplit in: >#{path}<"
+
+    ##  ["Date", "HomeTeam", "AwayTeam", "FTHG", "FTAG", "HTHG", "HTAG"]
+    puts "columns:"
+    pp columns
+
+    text = File.open( path, 'r:utf-8' ).read   ## note: make sure to use (assume) utf-8
+
+    ## note: do NOT use headers
+    ##   for easy sorting use "plain" array of array for records
+    csv_options = { col_sep: sep }
+
+    data = CSV.parse( text, csv_options )
+
+    ## todo/check: (auto-) strip (remove all leading and trailing spaces)
+    ##     from all values - why? why not?
+    ##   check if CSV.parse has an option for it?
+
+    headers = data.shift   ## remove top array item (that is, row with headers)
+
+    header_mapping = {}
+    headers.each_with_index  { | header,i | header_mapping[header]=i }
+    pp header_mapping
+
+    ## map columns to array indices e.g. ['Season', 'Div'] => [1,2]
+    column_indices = columns.map { |col| header_mapping[col] }
+    pp column_indices
+
+
+    ###################################################
+    ## note: sort data by columns (before split)
+    data = data.sort do |row1,row2|
+       res = 0
+       column_indices.each do |col|
+         res = row1[col] <=> row2[col]    if res == 0
+       end
+       res
+    end
+
+    chunk = []
+    data.each_with_index do |row,i|
+      chunk << row
+
+      next_row = data[i+1]
+
+      changed = false
+      if next_row.nil?   ## end-of-file
+        changed = true
+      else
+        column_indices.each do |col|
+          if row[col] != next_row[col]
+             changed = true
+             break   ## out of each column_indices loop
+           end
+        end
+      end
+
+      if changed
+        puts "save new chunk:"
+        column_values = column_indices.map {|col| row[col] }
+        pp column_values
+
+        # note: add header(s) row upfront (as first row) to chunk (with unshift)
+        chunk_with_headers = chunk.unshift( headers )
+        if blk
+          yield( column_values, chunk_with_headers )
+        else
+          ## auto-save (write-to-file) by default - why? why not?
+          split_write( path, column_values, chunk_with_headers )
+        end
+
+        chunk = []   ## reset chunk for next batch of records
+      end
+    end
+
+    puts 'Done.'
+  end  ## method self.split
+
+
+  def self.split_write( inpath, values, chunk )
+    basename = File.basename( inpath, '.*' )
+    dirname  = File.dirname( inpath )
+
+    ## check/change invalid filename chars
+    ##  e.g. change 1990/91 to 1990-91
+    extraname = values.map {|value| value.tr('/','-')}.join('~')
+
+    outpath = "#{dirname}/#{basename}_#{extraname}.csv"
+    puts "saving >#{basename}_#{extraname}.csv<..."
+
+    CSV.open( outpath, 'w:utf-8' ) do |out|
+      chunk.each do |row|
+        out << row
+      end
+    end
+  end
+
+end # class CsvUtils