diff --git a/config/unitex-template.yaml b/config/unitex-template.yaml
index 46b04df25ff7180aa81dc76a340af5ce38189558..a4c7c03d2f7d822f4a7a135fa25e7915fa755884 100644
--- a/config/unitex-template.yaml
+++ b/config/unitex-template.yaml
@@ -1,66 +1,68 @@
-# Do not modify this file. Use the 'build-config-file.py' script to generate a
-# working version adapted to you local Unitex installation or copy this file
-# before editing.
+# Do not modify this file. Use the 'build-config-file.py' script to
+# generate a working version adapted to you local Unitex installation
+# or copy this file before editing.
# The 'global' section contains the global configuration parameters.
global:
# There is 3 'debug' level:
# 0: the error output is disabled;
- # 1: the error output is limited to the logging system implemented in the
- # bindings;
- # 2: the error output is activated for both the bindings and the Unitex
- # processor.
- # NOTE: if you activate the debug for level >= 1, the verbose level is
- # automatically activated at level 2.
+ # 1: the error output is limited to the logging system implemented
+ # in the bindings;
+ # 2: the error output is activated for both the bindings and the
+ # Unitex processor.
+ # NOTE: if you activate the debug for level >= 1, the verbose level
+ # is automatically activated at level 2.
debug: 0
# There is 4 'verbose' level:
# 0: the standard output is disabled;
- # 1: the standard output shows 'warnings' emitted by the bindings logging
- # system;
+ # 1: the standard output shows 'warnings' emitted by the bindings
+ # logging system;
# 2: the standard output shows 'warnings' and various processing
# informations emitted by the bindings logging system;
- # 3: the full standard output is activated for both the bindings and the
- # Unitex processor.
+ # 3: the full standard output is activated for both the bindings and
+ # the Unitex processor.
verbose: 0
- # If not 'null', the error and standard outputs are redirected to the file
- # specified by this parameters. Be sure to have write access to this file.
+ # If not 'null', the error and standard outputs are redirected to
+ # the file specified by this parameters. Be sure to have write
+ # access to this file.
#log: /var/log/unitex.log
log: null
# If you are using the high-level 'Processor' class, this parameter
# activate or deactivate the resource persistence. If persistency is
- # activated, dictionaries, grammar and alphabet are loaded during the
- # object initialization and kept in memory in order to improve
+ # activated, dictionaries, grammar and alphabet are loaded during
+ # the object initialization and kept in memory in order to improve
# performances.
# NOTE: you can manually activate the persistence by using the
# 'load_persistent_X' functions from 'unitex.resources'.
persistence: True
- # The Unitex library implements a virtual filesystem which avoids a lot
- # of I/O and improves the performance. If this parameter is set to True,
- # The high-level 'Processor' class will activate automatically this virtual
- # filesystem.
- # NOTE: as for the persistence, you can activate manually the VFS by using
- # the functions from 'unitex.io'.
+ # The Unitex library implements a virtual filesystem which avoids a
+ # lot of I/O and improves the performance. If this parameter is set
+ # to True, the high-level 'Processor' class will activate
+ # automatically this virtual filesystem.
+ # NOTE: as for the persistence, you can activate manually the VFS by
+ # using the functions from 'unitex.io'.
virtualization: True
-# The 'resources' section is automatically filled by the 'build-config-file.py'
-# script. If you want to do it manually, be sure to give the absolute path of
-# each resource as shown below.
-# NOTE: the 'dictionaries' parameter is a list of path. As required by the YAML
-# format, each item must be prefixed by the '-' character (cf. example).
-# resources:
-# language: fr
-# alphabet: /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Alphabet.txt
-# alphabet-sorted: /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Alphabet_sort.txt
-# sentence: /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Graphs/Preprocessing/Sentence/Sentence.fst2
-# replace: /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Graphs/Preprocessing/Replace/Replace.fst2
-# dictionaries:
-# - /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Dela/dela-fr-public.bin
-# - /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Dela/ajouts80jours.bin
-# - /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Dela/motsGramf-.bin
+# The 'resources' section is automatically filled by the
+# 'build-config-file.py' script. If you want to do it manually, be sure
+# to give the absolute path of each resource as shown below.
+# NOTE: the 'dictionaries' parameter is a list of path. As required by
+# the YAML format, each item must be prefixed by the '-' character
+# (cf. example).
+#resources:
+# language: fr
+# alphabet: /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Alphabet.txt
+# alphabet-sorted: /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Alphabet_sort.txt
+# sentence: /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Graphs/Preprocessing/Sentence/Sentence.fst2
+# replace: /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Graphs/Preprocessing/Replace/Replace.fst2
+# dictionaries:
+# - /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Dela/dela-fr-public.bin
+# - /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Dela/ajouts80jours.bin
+# - /home/dev/projects/python-unitex/dependencies/Unitex-GramLab-3.1rc/French/Dela/motsGramf-.bin
resources:
language: null
@@ -71,25 +73,25 @@ resources:
dictionaries: null
-# The 'tools' section can contain any of the arguments used by the unitex
-# tools.
-# Most of the times, these parameters are the same than the one used by the
-# original Unitex tools (as described in the Unitex manual). Changes are
-# explained in the comments of this file.
-# NOTE: if you use the 'Processor' high-level class some parameters will be
-# overriden to fit the 'tag' functions behaviour. For instance, there is
-# no point to define a font or a context for 'concord'.
+# The 'tools' section can contain any of the arguments used by the
+# unitex tools.
+# Most of the times, these parameters are the same than the one used by
+# the original Unitex tools (as described in the Unitex manual). Changes
+# are explained in the comments of this file.
+# NOTE: if you use the 'Processor' high-level class some parameters will
+# be overriden to fit the 'tag' functions behaviour. For instance,
+# there is no point to define a font or a context for 'concord'.
# NOTE: ALL FILE PATH MUST BE ABSOLUTE!!!
tools:
# CheckDic command (Unitex manual, p.266)
check_dic:
- # If set to True, the function will use a strict syntax checking
+ # If set to True, the function will use a strict syntax checking
# against unprotected dot and comma.
strict: False
- # If set to True, the function will tolerate spaces in grammatical,
- # semantic and inflectional codes.
+ # If set to True, the function will tolerate spaces in
+ # grammatical, semantic and inflectional codes.
no_space_warning: False
# Compress command (Unitex manual, p.266)
@@ -98,9 +100,10 @@ tools:
# produce a file xxx.bin.
output: null
- # If set to True, 'flip' indicates that the inflected and canonical
- # forms should be swapped in the compressed dictionary. This option is
- # used to construct an inverse dictionary.
+ # If set to True, 'flip' indicates that the inflected and
+ # canonical forms should be swapped in the compressed
+ # dictionary. This option is used to construct an inverse
+ # dictionary.
flip: False
# If set to True, the function will use the semitic compression
@@ -108,45 +111,48 @@ tools:
semitic: False
# 'version: v1' produces an old style .bin file.
- # 'version: v2' produces a new style .bin file, with no file size
- # limitation to 16 Mb and a smaller resulting size.
+ # 'version: v2' produces a new style .bin file, with no file
+ # size limitation to 16 Mb and a smaller resulting
+ # size.
version: v2
# Concord command (Unitex manual, p.267)
concord:
- # 'font' specifies the name of the font to use if the output is an
- # HTML file.
+ # 'font' specifies the name of the font to use if the output is
+ # an HTML file.
#font: "Courier new"
font: null
- # 'fontsize' specifies the font size to use if the output is an HTML
- # file.
+ # 'fontsize' specifies the font size to use if the output is an
+ # HTML file.
#fontsize: 12
fontsize: null
- # If 'only_ambiguous' is set to True, the function will only displays
- # identical occurrences with ambiguous outputs, in text order.
+ # If 'only_ambiguous' is set to True, the function will only
+ # displays identical occurrences with ambiguous outputs, in text
+ # order.
only_ambiguous: False
- # If 'only_matches' is set to True, the function will force empty right
- # and left contexts. Moreover, if used with -t/–text, the function will
- # not surround matches with tabulations.
+ # If 'only_matches' is set to True, the function will force
+ # empty right and left contexts. Moreover, if used with 'text',
+ # the function will not surround matches with tabulations.
only_matches: False
# 'left' specifies the number of characters on the left of the
- # occurrences. In Thai mode, this means the number of non-diacritic
- # characters. For both 'left' and 'right' parameters, you can add the
- # 's' character to stop at the first {S} tag. For instance, if you set
- # '40s' for the left value, the left context will end at 40 characters
- # at most, less if the {S} tag is found before.
+ # occurrences. In Thai mode, this means the number of
+ # non-diacritic characters. For both 'left' and 'right'
+ # parameters, you can add the 's' character to stop at the first
+ # {S} tag. For instance, if you set '40s' for the left value,
+ # the left context will end at 40 characters at most, less if
+ # the {S} tag is found before.
# NOTE: the number must be quoted to avoid integer conversion.
left: "0"
- # 'right' specifies the number of characters (non-diacritic ones in
- # Thai mode) on the right of the occurrences. If the occurrence is
- # shorter than this value, the concordance line is completed up to
- # right. If the occurrence is longer than the length defined by right,
- # it is nevertheless saved as whole.
+ # 'right' specifies the number of characters (non-diacritic ones
+ # in Thai mode) on the right of the occurrences. If the
+ # occurrence is shorter than this value, the concordance line is
+ # completed up to right. If the occurrence is longer than the
+ # length defined by right, it is nevertheless saved as whole.
# NOTE: the number must be quoted to avoid integer conversion.
right: "0"
@@ -164,101 +170,107 @@ tools:
# 'format' specifies the output format. Possible values are:
# - html: produces a concordance in HTML format;
# - text: produces a concordance in text format;
- # - glossanet: produces a concordance for GlossaNet in HTML format
- # where occurrences are links described by the 'script'
- # parameter;
- # - script: produces a HTML concordance file where occurrences are
- # links described by the 'script' parameter;
- # - index: produces an index of the concordance, made of the content
- # of the occurrences (with the grammar outputs, if any),
- # preceded by the positions of the occurrences in the text
- # file given in characters;
+ # - glossanet: produces a concordance for GlossaNet in HTML
+ # format where occurrences are links described by
+ # the 'script' parameter;
+ # - script: produces a HTML concordance file where occurrences
+ # are links described by the 'script' parameter;
+ # - index: produces an index of the concordance, made of the
+ # content of the occurrences (with the grammar
+ # outputs, if any), preceded by the positions of the
+ # occurrences in the text file given in characters;
# - uima: produces an index of the concordance relative to the
# original text file, before any Unitex operation. The
# 'offsets' parameter must be provided;
- # - prlg: produces a concordance for PRLG corpora where each line is
- # prefixed by information extracted with Unxmlize’s 'prlg'
- # option. You must provide both the 'offsets' and the
- # 'unxmlize' parameter;
+ # - prlg: produces a concordance for PRLG corpora where each
+ # line is prefixed by information extracted with
+ # Unxmlize’s 'prlg' option. You must provide both the
+ # 'offsets' and the 'unxmlize' parameter;
# - xml: produces xml index of the concordance;
- # - xml-with-header: produces an xml index of the concordance with
- # full xml header;
- # - axis: quite the same as 'index', but the numbers represent the
- # median character of each occurrence;
- # - xalign: another index file, used by the text alignment module.
- # Each line is made of 3 integers X Y Z followed by the
- # content of the occurrence. X is the sentence number,
- # starting from 1. Y and Z are the starting and ending
- # positions of the occurrence in the sentence, given in
- # characters;
- # - merge: indicates to the function that it is supposed to produce
- # a modified version of the text and save it in a file. The
- # filename must be provided with the 'output' parameter.
+ # - xml-with-header: produces an xml index of the concordance
+ # with full xml header;
+ # - axis: quite the same as 'index', but the numbers represent
+ # the median character of each occurrence;
+ # - xalign: another index file, used by the text alignment
+ # module. Each line is made of 3 integers X Y Z
+ # followed by the content of the occurrence. X is
+ # the sentence number, starting from 1. Y and Z are
+ # the starting and ending positions of the
+ # occurrence in the sentence, given in characters;
+ # - merge: indicates to the function that it is supposed to
+ # produce a modified version of the text and save it
+ # in a file. The filename must be provided with the
+ # 'output' parameter.
format: "text"
- # 'script' describes the links format for 'glossanet' and 'script'
- # output. For instance, if you use 'http://www.google.com/search?q=',
- # you will obtain a HTML concordance file where occurrences are
- # hyperlinks to Google queries.
+ # 'script' describes the links format for 'glossanet' and
+ # 'script' output. For instance, if you use
+ # 'http://www.google.com/search?q=', you will obtain a
+ # HTML concordance file where occurrences are hyperlinks to
+ # Google queries.
script: null
- # 'offsets' provides the file produced by tokenize’s output_offsets
- # option (needed by the 'uima' and the 'prlg' format).
+ # 'offsets' provides the file produced by tokenize’s
+ # output_offsets option (needed by the 'uima' and the 'prlg'
+ # format).
offsets: null
- # 'unxmlize' provides the file produced by Unxmlize’s 'prlg' option
- # (needed by the 'prlg' format).
+ # 'unxmlize' provides the file produced by Unxmlize’s 'prlg'
+ # option (needed by the 'prlg' format).
unxmlize: null
- # 'directory' indicates to the function that it must not work in the
- # same directory than <index> but in 'directory'
+ # 'directory' indicates to the function that it must not work in
+ # the same directory than <index> but in 'directory'.
directory: null
- # If set to True, 'thai' indicates that the input text is in Thai
- # language
+ # If set to True, 'thai' indicates that the input text is in
+ # Thai language.
thai: False
# Dico command (Unitex manual, p.272)
dico:
- # 'morpho' lists dictionaries to load in morphological mode, if needed
- # by some .fst2 dictionaries.
+ # 'morpho' lists dictionaries to load in morphological mode, if
+ # needed by some .fst2 dictionaries.
morpho: null
- # If set to True, 'korean' indicates that the input text is in korean
- # language.
+ # If set to True, 'korean' indicates that the input text is in
+ # korean language.
korean: False
- # If set to True, 'semitic' indicates that the input text is in a
- # semitic language.
+ # If set to True, 'semitic' indicates that the input text is in
+ # a semitic language.
semitic: False
- # 'arabic_rules' specifies the Arabic typographic rule configuration
- # file path.
+ # 'arabic_rules' specifies the Arabic typographic rule
+ # configuration file path.
arabic_rules: null
- # 'raw' specifies and alternative output file path containing both
- # simple and compound words, without requiring a text directory.
+ # 'raw' specifies and alternative output file path containing
+ # both simple and compound words, without requiring a text
+ # directory.
raw: null
# Extract command (Unitex manual, p.277)
extract:
- # If set to True, 'non_matching_sentences' indicates to the function
- # to extract all sentences that don’t contain matching units.
+ # If set to True, 'non_matching_sentences' indicates to the
+ # function to extract all sentences that don’t contain matching
+ # units.
non_matching_sentences: False
# Fst2Txt command (Unitex manual, p.280)
fst2txt:
- # If set to True, the search will start at any position in the text,
- # even before a space. This parameter should only be used to carry out
- # morphological searches.
+ # If set to True, the search will start at any position in the
+ # text, even before a space. This parameter should only be used
+ # to carry out morphological searches.
start_on_space: False
- # If set to True, the function will work in character by character
- # tokenization mode. This is useful for languages like Thai.
+ # If set to True, the function will work in character by
+ # character tokenization mode. This is useful for languages like
+ # Thai.
word_by_word: False
- # If set to True, the function merge (instead of replace) transducer
- # outputs with text inputs.
+ # If set to True, the function merge (instead of replace)
+ # transducer outputs with text inputs.
merge: True
# Grf2Fst2 command (Unitex manual, p.280)
@@ -266,26 +278,28 @@ tools:
# If set to True, 'loop_check' enables error (loop) checking.
loop_check: False
- # If set to True, tokenization will be done character by character.
+ # If set to True, tokenization will be done character by
+ # character.
char_by_char: False
- # 'pkgdir' specifies the repository directory to use (see section
- # 5.2.2, p.99).
+ # 'pkgdir' specifies the repository directory to use (see
+ # section 5.2.2, p.99).
pkgdir: null
- # If set to True, no warning will be emitted when a graph matches the
- # empty word.
+ # If set to True, no warning will be emitted when a graph
+ # matches the empty word.
no_empty_graph_warning: False
- # If set to True, the function checks wether the given graph can be
- # considered as a valid sentence automaton or not.
+ # If set to True, the function checks wether the given graph can
+ # be considered as a valid sentence automaton or not.
tfst_check: False
# If set to True, the function does not print the graph names.
silent_grf_name: True
- # 'named_repository' must be a list of X=Y sequences, separated by ‘;’,
- # where X is the name of the repository denoted by pathname Y.
+ # 'named_repository' must be a list of X=Y sequences, separated
+ # by ‘;’, where X is the name of the repository denoted by
+ # pathname Y.
named_repository: null
# If set to True, the graph is compiled in debug mode.
@@ -297,95 +311,104 @@ tools:
# Locate command (Unitex manual, p.283)
locate:
- # If set to True, the search will start at any position in the text,
- # even before a space. This parameter should only be used to carry out
- # morphological searches.
+ # If set to True, the search will start at any position in the
+ # text, even before a space. This parameter should only be used
+ # to carry out morphological searches.
start_on_space: False
- # If set to True, tokenization will be done character by character.
+ # If set to True, tokenization will be done character by
+ # character.
char_by_char: False
- # 'morpho' lists dictionaries to load in morphological mode, if needed
- # by some .fst2 dictionaries.
+ # 'morpho' lists dictionaries to load in morphological mode, if
+ # needed by some .fst2 dictionaries.
morpho: null
- # If set to True, 'korean' indicates that the input text is in korean
- # language.
+ # If set to True, 'korean' indicates that the input text is in
+ # korean language.
korean: False
- # 'arabic_rules' specifies the Arabic typographic rule configuration
- # file path.
+ # 'arabic_rules' specifies the Arabic typographic rule
+ # configuration file path.
arabic_rules: null
- # If not null, the function puts produced files in 'sntdir' instead
- # of the text directory. Note that 'sntdir' must end with a file
- # separator (\ or /).
+ # If not null, the function puts produced files in 'sntdir'
+ # instead of the text directory. Note that 'sntdir' must end
+ # with a file separator (\ or /).
sntdir: null
- # This parameter specifies the negation operator to be used in Locate
- # patterns. The two legal values for X are 'minus' and 'tilde'.
+ # This parameter specifies the negation operator to be used in
+ # Locate patterns. The two legal values for X are 'minus' and
+ # 'tilde'.
negation_operator: "tilde"
# If not null, the function stops after the first N matches. By
# default, the function searches for all matches.
number_of_matches: null
- # 'stop_token_count' is a list of two integers. If specified, the
- # function will emit a warning after 'int_1' iterations on a token and
- # stops after 'int_2' iterations.
+ # 'stop_token_count' is a list of two integers. If specified,
+ # the function will emit a warning after 'int_1' iterations on a
+ # token and stops after 'int_2' iterations.
#stop_token_count=[3,5]
stop_token_count: null
- # Possible values for 'match_mode' are: 'longest', 'shortest' and 'all'
+ # Possible values for 'match_mode' are: 'longest', 'shortest'
+ # and 'all'.
match_mode: "longest"
# Possible values for 'output_mode' are:
# - 'ignore': the transducer outputs will be ignored;
- # - 'merge': the transducer outputs will be merged with the input
- # text;
- # - 'replace': the transducer outputs replaces the matching text.
+ # - 'merge': the transducer outputs will be merged with the
+ # input text;
+ # - 'replace': the transducer outputs replaces the matching
+ # text.
output_mode: "merge"
- # If set to True, this parameter enables special characters protection
- # when 'merge' or 'replace' mode is used. This is useful when Locate is
- # called by Dico in order to avoid producing bad lines like:
+ # If set to True, this parameter enables special characters
+ # protection when 'merge' or 'replace' mode is used. This is
+ # useful when Locate is called by Dico in order to avoid
+ # producing bad lines like:
# 3,14,.PI.NUM
protect_dic_chars: True
- # If not null, this parameter must be a list of two strings, where:
- # 'str_1' is a variable name whith content 'str_2'.
+ # If not null, this parameter must be a list of two strings,
+ # where: 'str_1' is a variable name whith content 'str_2'.
# NOTE: 'str_2' must be ASCII.
variable: null
# If set to True, the function allows the production of several
- # matches with same input but different outputs. If False, in case of
- # ambiguous outputs, one will be arbitrarily chosen and kept,
- # depending on the internal state of the function.
+ # matches with same input but different outputs. If False, in
+ # case of ambiguous outputs, one will be arbitrarily chosen and
+ # kept, depending on the internal state of the function.
ambiguous_outputs: True
# Possible values are:
- # - 'exit': kills the function if variable has an empty content;
+ # - 'exit': kills the function if variable has an empty
+ # content;
# - 'ignore': ignore the errors;
# - 'backtrack': stop the current path exploration.
variable_error: "ignore"
# Normalize command (Unitex manual, p.287)
normalize:
- # If set to True, every separator sequence will be turned into a single
- # space.
+ # If set to True, every separator sequence will be turned into a
+ # single space.
no_carriage_return: False
- # 'input_offsets' specifies the base offset file path to be used.
+ # 'input_offsets' specifies the base offset file path to be
+ # used.
input_offsets: null
- # 'output_offsets' specifies the offset file path to be produced.
+ # 'output_offsets' specifies the offset file path to be
+ # produced.
output_offsets: null
- # 'replacement_rules' specifies the normalization rule file to be used.
+ # 'replacement_rules' specifies the normalization rule file to
+ # be used.
replacement_rules: null
- # If set to True, the function only applies replacement rules specified
- # with the 'replacement_rules' parameter.
+ # If set to True, the function only applies replacement rules
+ # specified with the 'replacement_rules' parameter.
no_separator_normalization: False
# SortTxt command (Unitex manual, p.291)
@@ -397,54 +420,57 @@ tools:
reverse: False
# The 'sort_order' parameter specifies the file path of the
- # 'Alphabet_sort.txt' file or any other file defining the alphabet
- # order.
+ # 'Alphabet_sort.txt' file or any other file defining the
+ # alphabet order.
sort_order: null
- # If not null, the function backups the number of lines of the result
- # file in the file specified by this parameter.
+ # If not null, the function backups the number of lines of the
+ # result file in the file specified by this parameter.
line_info: null
- # If set to True, 'thai' indicates that the input text is in Thai
- # language
+ # If set to True, 'thai' indicates that the input text is in
+ # Thai language.
thai: False
- # If set to True, the function makes two entries XXX,YYY.ZZZ:A and
- # XXX,YYY.ZZZ:B become a single entry: XXX,YYY.ZZZ:A:B
+ # If set to True, the function makes two entries X,Y.Z:A and
+ # X,Y.Z:B become a single entry: X,Y.Z:A:B
factorize_inflectional_codes: False
# Tokenize command (Unitex manual, p.294)
tokenize:
- # If set to True, the function is applied character by character, with
- # the exceptions of the sentence delimiter {S}, the stop marker {STOP}
- # and lexical tags like {today,.ADV} which are considered to be single
- # units.
+ # If set to True, the function is applied character by
+ # character, with the exceptions of the sentence delimiter {S},
+ # the stop marker {STOP} and lexical tags like {today,.ADV}
+ # which are considered to be single units.
char_by_char: False
- # 'tokens' specifies the path of the 'tokens.txt' file to loa and
- # modify, instead of creating a new one from scratch.
+ # 'tokens' specifies the path of the 'tokens.txt' file to load
+ # and modify, instead of creating a new one from scratch.
tokens: null
- # 'input_offsets' specifies the base offset file path to be used.
+ # 'input_offsets' specifies the base offset file path to be
+ # used.
input_offsets: null
- # 'output_offsets' specifies the offset file path to be produced.
+ # 'output_offsets' specifies the offset file path to be
+ # produced.
output_offsets: null
# Txt2Tfst command (Unitex manual, p.296)
txt2tfst:
- # If set to True, 'clean' indicates whether the rule of conservation of
- # the best paths (see section 7.2.4) should be applied.
+ # If set to True, 'clean' indicates whether the rule of
+ # conservation of the best paths (see section 7.2.4) should be
+ # applied.
clean: False
- # This parameter specifies the file path of a normalization grammar
- # that is to be applied to the text automaton.
+ # This parameter specifies the file path of a normalization
+ # grammar that is to be applied to the text automaton.
normalization_grammar: null
- # This parameter specifies the Elag tagset file to use to normalize
- # dictionary entries.
+ # This parameter specifies the Elag tagset file to use to
+ # normalize dictionary entries.
tagset: null
- # If set to True, 'korean' indicates that the input text is in korean
- # language.
+ # If set to True, 'korean' indicates that the input text is
+ # in korean language.
korean: False