textutils 0.5.13 → 0.6.0

data/Manifest.txt

@@ -8,6 +8,7 @@ lib/textutils/filter/comment_filter.rb
 lib/textutils/filter/erb_django_filter.rb
 lib/textutils/filter/erb_filter.rb
 lib/textutils/helper/address_helper.rb
+lib/textutils/helper/tag_helper.rb
 lib/textutils/helper/title_helper.rb
 lib/textutils/helper/unicode_helper.rb
 lib/textutils/helper/value_helper.rb

data/lib/textutils/helper/address_helper.rb

@@ -4,31 +4,33 @@
 module TextUtils
   module AddressHelper
 
-  def normalize_address( old_address_line )
+  def normalize_addr( old_address )
     # for now only checks german 5-digit zip code
     #
     #  e.g.  Alte Plauener Straße 24 // 95028 Hof  becomes
     #        95028 Hof // Alte Plauener Straße 24 
 
-    new_address_line = old_address_line   # default - do nothing - just path through
+    new_address = old_address   # default - do nothing - just path through
 
-    lines = old_address_line.split( '//' )
+    lines = old_address.split( '//' )
 
     if lines.size == 2   # two lines / check for switching lines
       line1 = lines[0].strip
       line2 = lines[1].strip
       if line2 =~ /^[0-9]{5}\s/
-        new_address_line = "#{line2} // #{line1}"   # swap - let line w/ 5-digit zip code go first
+        new_address = "#{line2} // #{line1}"   # swap - let line w/ 5-digit zip code go first
       end
     end
 
-    new_address_line
+    new_address
   end
-  
+
 
   #  todo/fix: add _in_adr or _in_addr to name - why? why not?
+  #  -- make country_key optional - why? why not?
+  #      n move to second pos; use opts={} why? why not?
 
-  def find_city_for_country( country_key, address )
+  def find_city_in_addr( address, country_key )
 
     return nil if address.blank?    # do NOT process nil or empty address lines; sorry
 

data/lib/textutils/helper/tag_helper.rb

@@ -0,0 +1,35 @@
+# encoding: utf-8
+
+module TextUtils
+  module TagHelper
+
+
+  def find_tags( value )
+    # logger.debug "   found tags: >>#{value}<<"
+
+    tag_keys = value.split('|')
+
+    ## unify; replace _w/ space; remove leading n trailing whitespace
+    tag_keys = tag_keys.map do |key|
+      key = key.gsub( '_', ' ' )
+      key = key.strip
+      key
+    end
+
+    tag_keys # return tag keys as ary
+  end
+
+  def find_tags_in_attribs!( attribs )
+    # NB: will remove :tags from attribs hash
+
+    if attribs[:tags].present?
+      tag_keys = find_tags( attribs[:tags] )
+      attribs.delete(:tags)
+      tag_keys   # return tag keys as ary of strings
+    else
+      []  # nothing found; return empty ary
+    end
+  end
+
+  end # module TagHelper
+end # module TextUtils

data/lib/textutils/helper/value_helper.rb

@@ -5,16 +5,79 @@ module TextUtils
   module ValueHelper
 
 
+  def match_country( value )
+    if value =~ /^country:/   ## country:
+      country_key = value[8..-1]  ## cut off country: prefix
+      country = Country.find_by_key!( country_key )
+      yield( country )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+
   def is_region?( value )
     # assume region code e.g. TX or N
     value =~ /^[A-Z]{1,2}$/
   end
 
+  ## fix/todo: use match_region_for_country! w/ !!! why? why not?
+  def match_region_for_country( value, country_id )  ## NB: required country_id 
+    if value =~ /^region:/   ## region:
+      region_key = value[7..-1]  ## cut off region: prefix
+      region = Region.find_by_key_and_country_id!( region_key, country_id )
+      yield( region )
+      true  # bingo - match found
+    elsif is_region?( value )  ## assume region code e.g. TX or N
+      region = Region.find_by_key_and_country_id!( value.downcase, country_id )
+      yield( region )
+      true  # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+
+  def match_city( value )
+    if value =~ /^city:/   ## city:
+      city_key = value[5..-1]  ## cut off city: prefix
+      city = City.find_by_key( city_key )
+      yield( city )  # NB: might be nil (city not found)
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+
+  def match_brewery( value )
+    if value =~ /^by:/   ## by:  -brewed by/brewery
+      brewery_key = value[3..-1]  ## cut off by: prefix
+      brewery = Brewery.find_by_key!( brewery_key )
+      yield( brewery )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+
   def is_year?( value )
     # founded/established year e.g. 1776
     value =~ /^[0-9]{4}$/
   end
 
+  def match_year( value )
+    if is_year?( value )  # founded/established year e.g. 1776
+      yield( value.to_i )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+
   def is_website?( value )
     # check for url/internet address e.g. www.ottakringer.at
     #  - must start w/  www. or
@@ -24,6 +87,18 @@ module TextUtils
     value =~ /^www\.|\.com$/
   end
 
+  def match_website( value )
+    if is_website?( value )   # check for url/internet address e.g. www.ottakringer.at
+      # fix: support more url format (e.g. w/o www. - look for .com .country code etc.)
+      yield( value )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+
+
   def is_address?( value )
     # if value includes // assume address e.g. 3970 Weitra // Sparkasseplatz 160
     value =~ /\/{2}/
@@ -34,10 +109,10 @@ module TextUtils
   end
 
 
-  def find_grade( text )  # NB: returns ary [grade,text] / two values
+  def find_grade( value )  # NB: returns ary [grade,value] / two values
     grade = 4  # defaults to grade 4  e.g  *** => 1, ** => 2, * => 3, -/- => 4
 
-    text = text.sub( /\s+(\*{1,3})\s*$/ ) do |_|  # NB: stars must end field/value
+    value = value.sub( /\s+(\*{1,3})\s*$/ ) do |_|  # NB: stars must end field/value
       if $1 == '***'
         grade = 1
       elsif $1 == '**'
@@ -50,10 +125,66 @@ module TextUtils
       ''  # remove * from title if found
     end
 
-    [grade,text]
+    [grade,value]
   end
 
 
+  def find_key_n_title( values )  # NB: returns ary [attribs,more_values] / two values
+
+    ## fix: add/configure logger for ActiveRecord!!!
+    logger = LogKernel::Logger.root
+
+    ### todo/fix: allow check - do NOT allow mixed use of with key and w/o key
+    ##  either use keys or do NOT use keys; do NOT mix in a single fixture file
+
+    ### support autogenerate key from first title value
+
+    # if it looks like a key (only a-z lower case allowed); assume it's a key
+    #   - also allow . in keys e.g. world.quali.america, at.cup, etc.
+    #   - also allow 0-9 in keys e.g. at.2, at.3.1, etc.
+
+    # fix/todo: add support for leading underscore _
+    #   or allow keys starting w/ digits?
+    if values[0] =~ /^([a-z][a-z0-9.]*[a-z0-9]|[a-z])$/    # NB: key must start w/ a-z letter (NB: minimum one letter possible)
+      key_col         = values[0]
+      title_col       = values[1]
+      more_values     = values[2..-1]
+    else
+      key_col         = '<auto>'
+      title_col       = values[0]
+      more_values     = values[1..-1]
+    end
+
+    attribs = {}
+
+    ## check title_col for grade (e.g. ***/**/*) and use returned stripped title_col if exits
+    grade, title_col = find_grade( title_col )
+
+    # NB: for now - do NOT include default grade e.g. if grade (***/**/*) not present; attrib will not be present too
+    if grade == 1 || grade == 2 || grade == 3  # grade found/present
+      logger.debug "   found grade #{grade} in title"
+      attribs[:grade] = grade
+    end
+
+    ## title (split of optional synonyms)
+    # e.g. FC Bayern Muenchen|Bayern Muenchen|Bayern
+    titles = title_col.split('|')
+
+    attribs[ :title ]    =  titles[0]
+
+    ## add optional synonyms if present
+    attribs[ :synonyms ] =  titles[1..-1].join('|')  if titles.size > 1
+
+    if key_col == '<auto>'
+      ## autogenerate key from first title
+      key_col = TextUtils.title_to_key( titles[0] )
+      logger.debug "   autogen key »#{key_col}« from title »#{titles[0]}«"
+    end
+
+    attribs[ :key ] = key_col
+
+    [attribs, more_values]
+  end
 
   end # module ValueHelper
 end # module TextUtils

data/lib/textutils/reader/hash_reader.rb

@@ -3,6 +3,38 @@
 
 # fix: move into TextUtils namespace/module!!
 
+
+## todo/fix: find a better name than HashReaderV2 (HashReaderPlus?) ??
+
+class HashReaderV2
+  include LogUtils::Logging
+
+  def initialize( name, include_path )
+    @name          = name
+    @include_path  = include_path
+  end
+
+  attr_reader :name
+  attr_reader :include_path
+
+  def each
+    path          = "#{include_path}/#{name}.yml"
+    reader        = HashReader.new( path )
+
+    logger.info "parsing data '#{name}' (#{path})..."
+
+    reader.each do |key, value|
+      yield( key, value )
+    end
+
+    ## fix: move Prop table to props gem - why? why not??
+    WorldDb::Models::Prop.create_from_fixture!( name, path )
+  end
+
+end # class HashReaderV2
+
+
+
 class HashReader
 
   include LogUtils::Logging

data/lib/textutils/reader/values_reader.rb

@@ -2,17 +2,50 @@
 
 # fix: move into TextUtils namespace/module!!
 
+## todo/fix: find a better name than HashReaderV2 (HashReaderPlus?) ??
+
+class ValuesReaderV2
+  include LogUtils::Logging
+
+  def initialize( name, include_path, more_attribs={} )
+    @name          = name
+    @include_path  = include_path
+    @more_attribs  = more_attribs
+  end
+
+  attr_reader :name
+  attr_reader :include_path
+  attr_reader :more_attribs
+
+  def each_line
+    path          = "#{include_path}/#{name}.txt"
+    reader        = ValuesReader.new( path, more_attribs )
+
+    logger.info "parsing data '#{name}' (#{path})..."
+
+    reader.each_line do |attribs, values|
+      yield( attribs, values )
+    end
+
+    ## fix: move Prop table to props gem - why? why not??
+    WorldDb::Models::Prop.create_from_fixture!( name, path )
+  end
+
+end # class ValuesReaderV2
+
+
+
 class ValuesReader
 
   include LogUtils::Logging
   
-  include TextUtils::ValueHelper # e.g. includes find_grade()
+  include TextUtils::ValueHelper # e.g. includes find_grade, find_key_n_title
 
 
-  def initialize( path, more_values={} )
+  def initialize( path, more_attribs={} )
     @path = path
 
-    @more_values = more_values
+    @more_attribs = more_attribs
 
     @data = File.read_utf8( @path )
   end
@@ -29,8 +62,8 @@ class ValuesReader
   def each_line   # support multi line records
 
     inside_line = false   # todo: find a better name? e.g. line_found?
-    attribs = {}     # rename to new_attributes?
-    more_cols = []   # rename to more_values?
+    attribs = {}
+    more_values = []
       
 
     @data.each_line do |line|
@@ -73,15 +106,15 @@ class ValuesReader
          #  allows you to use any chars
          logger.debug "   multi-line record - add key-value »#{line}«"
 
-         more_cols.unshift( line.dup )   # add value upfront to array (first value); lets us keep (optional) tags as last entry; fix!! see valuereaderEx v2
+         more_values.unshift( line.dup )   # add value upfront to array (first value); lets us keep (optional) tags as last entry; fix!! see valuereaderEx v2
          next
       else
         # NB: new record clears/ends multi-line record
-        
+
         if inside_line  # check if we already processed a line? if yes; yield last line
-          yield( attribs, more_cols )
-          attribs   = {}
-          more_cols = []
+          yield( attribs, more_values )
+          attribs     = {}
+          more_values = []
         end
         inside_line = true
       end
@@ -91,14 +124,14 @@ class ValuesReader
       line = line.gsub( '\,', '♣' )  # use black club suit/=shamrock char for escaped separator
       
       ## use generic separator (allow us to configure separator)
-      line = line.gsub( ',', '♦')  # use black diamond suit for separator
+      line = line.gsub( ',', '›')
       
       ## restore escaped commas (before split)
       line = line.gsub( '♣', ',' )
 
       logger.debug "line: »#{line}«"
 
-      values = line.split( '♦' )
+      values = line.split( '›' )
       
       # pass 1) remove leading and trailing whitespace for values
 
@@ -115,67 +148,18 @@ class ValuesReader
           true
         end
       end
-      
-      logger.debug "  values: »#{values.join('« »')}«"
-      
-      
-      ### todo/fix: allow check - do NOT allow mixed use of with key and w/o key
-      ##  either use keys or do NOT use keys; do NOT mix in a single fixture file
-      
-      
-      ### support autogenerate key from first title value
-      
-      # if it looks like a key (only a-z lower case allowed); assume it's a key
-      #   - also allow . in keys e.g. world.quali.america, at.cup, etc.
-      #   - also allow 0-9 in keys e.g. at.2, at.3.1, etc.
-
-      # fix/todo: add support for leading underscore _
-      #   or allow keys starting w/ digits?
-      if values[0] =~ /^([a-z][a-z0-9.]*[a-z0-9]|[a-z])$/    # NB: key must start w/ a-z letter (NB: minimum one letter possible)
-        key_col         = values[0]
-        title_col       = values[1]
-        more_cols       = values[2..-1]
-      else
-        key_col         = '<auto>'
-        title_col       = values[0]
-        more_cols       = values[1..-1]
-      end
 
-      attribs = {}
+      logger.debug "  values: »#{values.join('« »')}«"
 
-      ## check title_col for grade (e.g. ***/**/*) and use returned stripped title_col if exits
-      grade, title_col = find_grade( title_col )
+      attribs, more_values = find_key_n_title( values )
 
-      # NB: for now - do NOT include default grade e.g. if grade (***/**/*) not present; attrib will not be present too
-      if grade == 1 || grade == 2 || grade == 3  # grade found/present
-        logger.debug "   found grade #{grade} in title"
-        attribs[:grade] = grade
-      end
+      attribs = attribs.merge( @more_attribs )  # e.g. merge country_id and other defaults if present
 
-      ## title (split of optional synonyms)
-      # e.g. FC Bayern Muenchen|Bayern Muenchen|Bayern
-      titles = title_col.split('|')
-      
-      attribs[ :title ]    =  titles[0]
-     
-      ## add optional synonyms if present
-      attribs[ :synonyms ] =  titles[1..-1].join('|')  if titles.size > 1
-      
-      if key_col == '<auto>'
-        ## autogenerate key from first title
-        key_col = TextUtils.title_to_key( titles[0] )
-        logger.debug "   autogen key »#{key_col}« from title »#{titles[0]}«, textutils version #{TextUtils::VERSION}"
-      end
-      
-      attribs[ :key ] = key_col
-      
-      attribs = attribs.merge( @more_values )  # e.g. merge country_id and other defaults if present
-                        
     end # each lines
 
     # do NOT forget to yield last line (if present/processed)
     if inside_line
-      yield( attribs, more_cols )
+      yield( attribs, more_values )
     end
 
 

data/lib/textutils/version.rb

@@ -1,6 +1,6 @@
 
 module TextUtils
 
-  VERSION = '0.5.13'
+  VERSION = '0.6.0'
 
 end   # module TextUtils

data/lib/textutils.rb

@@ -22,6 +22,7 @@ require 'textutils/filter/erb_django_filter'
 require 'textutils/filter/erb_filter'
 
 require 'textutils/helper/unicode_helper'
+require 'textutils/helper/tag_helper'
 require 'textutils/helper/title_helper'
 require 'textutils/helper/address_helper'
 require 'textutils/helper/value_helper'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: textutils
 version: !ruby/object:Gem::Version
-  version: 0.5.13
+  version: 0.6.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-05-14 00:00:00.000000000 Z
+date: 2013-05-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: logutils
-  requirement: &83466980 !ruby/object:Gem::Requirement
+  requirement: &84354180 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: '0.5'
   type: :runtime
   prerelease: false
-  version_requirements: *83466980
+  version_requirements: *84354180
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &83466720 !ruby/object:Gem::Requirement
+  requirement: &84353960 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: '3.10'
   type: :development
   prerelease: false
-  version_requirements: *83466720
+  version_requirements: *84353960
 - !ruby/object:Gem::Dependency
   name: hoe
-  requirement: &83466490 !ruby/object:Gem::Requirement
+  requirement: &84353740 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,7 +43,7 @@ dependencies:
         version: '3.3'
   type: :development
   prerelease: false
-  version_requirements: *83466490
+  version_requirements: *84353740
 description: textutils - Text Filters, Helpers, Readers and More
 email: webslideshow@googlegroups.com
 executables: []
@@ -61,6 +61,7 @@ files:
 - lib/textutils/filter/erb_django_filter.rb
 - lib/textutils/filter/erb_filter.rb
 - lib/textutils/helper/address_helper.rb
+- lib/textutils/helper/tag_helper.rb
 - lib/textutils/helper/title_helper.rb
 - lib/textutils/helper/unicode_helper.rb
 - lib/textutils/helper/value_helper.rb