# This is a sample output configuration for the
# IBM Word Cloud Generator; it also serves
# as documentation.

# Blank lines and lines beginning with the # character are ignored.
# Case *is* significant.

# Configuration files must be encoded as UTF-8 (therefore, ASCII is fine).

##########################################
# The following properties are MANDATORY #
##########################################

# Path to a TrueType font:

# e.g. windows:
font: simsun.ttc

# e.g. mac:
# font: /Library/Fonts/Times New Roman.ttf
# font: /Library/Fonts/Georgia.ttf

# for linux, download any TrueType font and point to it
# font: /opt/fonts/ttf/quelquechose.ttf

# NOTE: if you're using this sample to test, remember to change your
# working directory to the one containing this file, so that the relative
# path to the sample font will work for you. You could also replace it
# with the absolute path of one of your own truetype fonts.

# The structure of the input text.
#
# Possible values are:
#
#	text
#	tab
#
# "text" means unstructured text. The program will count words and
#		size the words in proportion to their frequencies.
# "tab" means tab-separated values, and requires further configuration
#		settings, below.
#
format: text

# The encoding of the input text.
#
# Possible values are:
#
#	US-ASCII
#	ISO-8859-1
#	UTF-8
#	UTF-16BE
#	UTF-16LE
#	UTF-16
#
inputencoding: UTF-8

#################################################################
# The following properties are MANDATORY for tab files          #
#################################################################

# How to treat the first line of structured data.
#
# Possible values:
#	data
#	skip
#	headings
#
# "data" means that the first line in the file is data. This
#		setting cause the "column" configuration options to
#		be understood as numeric indices, starting at 1.
# "skip" means throw away the first line, and look for numeric
#		indices in the "column" config options, as with "data".
# "headings" means that the first line contains column headings.
#		The "column" config options will be interpreted as the
#		text of the data headings.
#
# Ignored for input type "text".

# example
firstline: data

# How to interpret the structured data.

# Which column contains the "word"?
#
# For firstline values of "data" and "skip", this should be a
# column number, where the first column is column 1. For
# "heading", this should be the value of the heading for
# column containing the word or phrase to be rendered in the cloud.

# example numeric index
wordcolumn: 1

# examples with headings:
# wordcolumn: firstname
# wordcolumn: Heading With Spaces

# Which column contains the weight?
#
# For firstline values of "data" and "skip", this should be a
# column number, where the first column is column 1. For
# "heading", this should be the value of the heading for
# column containing the weight of the given word or phrase.
# The weight determines the word's relative size.

# example
weightcolumn: 2

# Which column contains the color? (OPTIONAL)
#
# You can provide your own color per word.
# Colors should be in the format
#    RRGGBB
# or
#    #RRGGBB
# or
#    0xRRGGBB
# where RR, GG, and BB are hexadecimal numbers
# between 00 and FF.
#
# For firstline values of "data" and "skip", this should be a
# column number, where the first column is column 1. For
# "heading", this should be the value of the heading for
# column containing the color of the given word or phrase.
#
# If this configuration is given, then palette settings (below)
# will be ignored.

# example
colorcolumn: 3


##########################################
# The following properties are OPTIONAL  #
##########################################

# Case folding -- send everything to upper or lower case
#
# Possible values: Upper, Lower
#
# Default: no case folding
#
# Example:
#
#casefold: Lower


# Background color
#
# Colors should be specified as in the colorcolumn setting, above.
# 
# Default:
background: FFFFFF

# Palette
#
# Colors should be specified as in the colorcolumn setting, above.
#
# Colors are assigned to words by randomly choosing from
# the provided palette. You can list any number of colors, and
# you can make a given color more likely
# than another by listing it more than once.
#
# Default:
palette: 880099, 339922, 993333, 2266CC

# Maximum number of words to show
#
# Default:
# maxwords: 150
# More fun:
maxwords: 800

# The "placement strategy" to use
# Possible values:
#
#   HorizontalCenterLine
#   VerticalCenterLine
#   Alphabetical
#   AlphabeticalVertical
#   Center
#
# Capitalization and spelling are significant.
#
# Default:
placement: Center

# The perimeter shape, either BLOBBY or SQUARISH
#
# Default:
shape: SQUARISH

# The "orientation strategy" to use.
# Possible values:
#
#	HORIZONTAL
#	MOSTLY_HORIZONTAL
#	HALF_AND_HALF
#	MOSTLY_VERTICAL
#	VERTICAL
#	ANY_WHICH_WAY
#
# Default:
orientation: HALF_AND_HALF
			
# Which collection of stopwords (ignored words) to use.
# One of:
#
#	Arabic, Catalan, Czech, Dutch, Danish, English, Esperanto,
#	Farsi, Finnish, French, German, Greek, Hebrew, Hindi, Hungarian,
#	Italian, Norwegian, Polish, Portuguese, Romanian, Russian,
#	Slovenian, Spanish, Swedish, Turkish
#
#	See stopwordsfile setting for custom stop words lists.
#
# No stopwords used by default.
#
# Example: 
stopwords: English

# Path to a file containing custom stopwords. 
# Stopwords should be given one per line in a text file.
#
# No stopwords file used by default.
# For the hamlet example, we might wish to remove the names that
# indicate the speaker
#stopwordsfile: hamlet-stopwords.txt

# If you use both the "stopwords" and "stopwordsfile" options
# the the program will load the given stopwords and append
# your custom list.

# Encoding of stopwords file, when using custom stopwords.
#
# Default:
stopwordsencoding: UTF-8

# Whether or not to treat numbers as stopwords
#
# true/false
#
# Default:
stripnumbers: true
