diff --git a/tests/amrbatch.log b/tests/amrbatch.log
index 1c35a300cf9b008105159c603298fedabe629b13..351bd692e15b12b69b2e71025ce9d054d1a65539 100644
--- a/tests/amrbatch.log
+++ b/tests/amrbatch.log
@@ -1,15 +1,57 @@
- INFO - [AMR Batch] NL Document Parsing
- INFO -
=== Preparation ===
-- INFO - -- base reference: test
-- INFO - -- input filepath: /home/lamenji/Workspace/Tetras/amrbatch/tests/input/test.txt
+- INFO - -- base reference: SSC-ABSTRACT
+- INFO - -- input filepath: /home/lamenji/Workspace/Tetras/amrbatch/tests/input/SSC-ABSTRACT.txt
- INFO - -- output dirpath: /home/lamenji/Workspace/Tetras/amrbatch/tests/output/Test-20230303/
- INFO - -- Reading input files to recover a list of sentences
- DEBUG - *** sentence 1 ***
-{'base_ref': 'test-01', 'number': 1, 'output_data_dir': 'test-01/', 'data_ref': 'test-01', 'id_line_str': '# ::id test-01\n', 'sentence': 'The sun is a star.', 'graph': ''}
+{'base_ref': 'SSC-ABSTRACT-01', 'number': 1, 'output_data_dir': 'SSC-ABSTRACT-01/', 'data_ref': 'SSC-ABSTRACT-01', 'id_line_str': '# ::id SSC-ABSTRACT-01\n', 'sentence': 'The Solar System is the gravitationally bound system of the Sun and the objects that orbit it, either directly or indirectly.', 'graph': ''}
- DEBUG - *** sentence 2 ***
-{'base_ref': 'test-02', 'number': 2, 'output_data_dir': 'test-02/', 'data_ref': 'test-02', 'id_line_str': '# ::id test-02\n', 'sentence': 'Earth is a planet.', 'graph': ''}
-- INFO - ----- number of sentences: 2
+{'base_ref': 'SSC-ABSTRACT-02', 'number': 2, 'output_data_dir': 'SSC-ABSTRACT-02/', 'data_ref': 'SSC-ABSTRACT-02', 'id_line_str': '# ::id SSC-ABSTRACT-02\n', 'sentence': 'Of the objects that orbit the Sun directly, the largest are the eight planets, with the remainder being smaller objects, the dwarf planets and small Solar System bodies.', 'graph': ''}
+- DEBUG - *** sentence 3 ***
+{'base_ref': 'SSC-ABSTRACT-03', 'number': 3, 'output_data_dir': 'SSC-ABSTRACT-03/', 'data_ref': 'SSC-ABSTRACT-03', 'id_line_str': '# ::id SSC-ABSTRACT-03\n', 'sentence': 'Of the objects that orbit the Sun indirectly—the natural satellites—two are larger than the smallest planet, Mercury, and one more almost equals it in size.', 'graph': ''}
+- DEBUG - *** sentence 4 ***
+{'base_ref': 'SSC-ABSTRACT-04', 'number': 4, 'output_data_dir': 'SSC-ABSTRACT-04/', 'data_ref': 'SSC-ABSTRACT-04', 'id_line_str': '# ::id SSC-ABSTRACT-04\n', 'sentence': 'The Solar System formed 4.6 billion years ago from the gravitational collapse of a giant interstellar molecular cloud.', 'graph': ''}
+- DEBUG - *** sentence 5 ***
+{'base_ref': 'SSC-ABSTRACT-05', 'number': 5, 'output_data_dir': 'SSC-ABSTRACT-05/', 'data_ref': 'SSC-ABSTRACT-05', 'id_line_str': '# ::id SSC-ABSTRACT-05\n', 'sentence': "The vast majority of the system's mass is in the Sun, with the majority of the remaining mass contained in Jupiter.", 'graph': ''}
+- DEBUG - *** sentence 6 ***
+{'base_ref': 'SSC-ABSTRACT-06', 'number': 6, 'output_data_dir': 'SSC-ABSTRACT-06/', 'data_ref': 'SSC-ABSTRACT-06', 'id_line_str': '# ::id SSC-ABSTRACT-06\n', 'sentence': 'The four smaller inner system planets, Mercury, Venus, Earth and Mars, are terrestrial planets, being primarily composed of rock and metal.', 'graph': ''}
+- DEBUG - *** sentence 7 ***
+{'base_ref': 'SSC-ABSTRACT-07', 'number': 7, 'output_data_dir': 'SSC-ABSTRACT-07/', 'data_ref': 'SSC-ABSTRACT-07', 'id_line_str': '# ::id SSC-ABSTRACT-07\n', 'sentence': 'The four outer system planets are giant planets, being substantially more massive than the terrestrials.', 'graph': ''}
+- DEBUG - *** sentence 8 ***
+{'base_ref': 'SSC-ABSTRACT-08', 'number': 8, 'output_data_dir': 'SSC-ABSTRACT-08/', 'data_ref': 'SSC-ABSTRACT-08', 'id_line_str': '# ::id SSC-ABSTRACT-08\n', 'sentence': 'The two largest planets, Jupiter and Saturn, are gas giants, being composed mainly of hydrogen and helium; the two outermost planets, Uranus and Neptune, are ice giants, being composed mostly of substances with relatively high melting points compared with hydrogen and helium, called volatiles, such as water, ammonia and methane.', 'graph': ''}
+- DEBUG - *** sentence 9 ***
+{'base_ref': 'SSC-ABSTRACT-09', 'number': 9, 'output_data_dir': 'SSC-ABSTRACT-09/', 'data_ref': 'SSC-ABSTRACT-09', 'id_line_str': '# ::id SSC-ABSTRACT-09\n', 'sentence': 'All eight planets have almost circular orbits that lie within a nearly flat disc called the ecliptic.', 'graph': ''}
+- DEBUG - *** sentence 10 ***
+{'base_ref': 'SSC-ABSTRACT-10', 'number': 10, 'output_data_dir': 'SSC-ABSTRACT-10/', 'data_ref': 'SSC-ABSTRACT-10', 'id_line_str': '# ::id SSC-ABSTRACT-10\n', 'sentence': 'The Solar System also contains smaller objects.', 'graph': ''}
+- DEBUG - *** sentence 11 ***
+{'base_ref': 'SSC-ABSTRACT-11', 'number': 11, 'output_data_dir': 'SSC-ABSTRACT-11/', 'data_ref': 'SSC-ABSTRACT-11', 'id_line_str': '# ::id SSC-ABSTRACT-11\n', 'sentence': 'The asteroid belt, which lies between the orbits of Mars and Jupiter, mostly contains objects composed, like the terrestrial planets, of rock and metal.', 'graph': ''}
+- DEBUG - *** sentence 12 ***
+{'base_ref': 'SSC-ABSTRACT-12', 'number': 12, 'output_data_dir': 'SSC-ABSTRACT-12/', 'data_ref': 'SSC-ABSTRACT-12', 'id_line_str': '# ::id SSC-ABSTRACT-12\n', 'sentence': "Beyond Neptune's orbit lie the Kuiper belt and scattered disc, which are populations of trans-Neptunian objects composed mostly of ices, and beyond them a newly discovered population of sednoids.", 'graph': ''}
+- DEBUG - *** sentence 13 ***
+{'base_ref': 'SSC-ABSTRACT-13', 'number': 13, 'output_data_dir': 'SSC-ABSTRACT-13/', 'data_ref': 'SSC-ABSTRACT-13', 'id_line_str': '# ::id SSC-ABSTRACT-13\n', 'sentence': 'Within these populations, some objects are large enough to have rounded under their own gravity, though there is considerable debate as to how many there will prove to be.', 'graph': ''}
+- DEBUG - *** sentence 14 ***
+{'base_ref': 'SSC-ABSTRACT-14', 'number': 14, 'output_data_dir': 'SSC-ABSTRACT-14/', 'data_ref': 'SSC-ABSTRACT-14', 'id_line_str': '# ::id SSC-ABSTRACT-14\n', 'sentence': 'Such objects are categorized as dwarf planets.', 'graph': ''}
+- DEBUG - *** sentence 15 ***
+{'base_ref': 'SSC-ABSTRACT-15', 'number': 15, 'output_data_dir': 'SSC-ABSTRACT-15/', 'data_ref': 'SSC-ABSTRACT-15', 'id_line_str': '# ::id SSC-ABSTRACT-15\n', 'sentence': 'Astronomers generally accept at least nine objects as dwarf planets: the asteroid Ceres and the trans-Neptunian objects Pluto, Eris, Haumea, Makemake, Gonggong, Quaoar, Sedna, and Orcus.', 'graph': ''}
+- DEBUG - *** sentence 16 ***
+{'base_ref': 'SSC-ABSTRACT-16', 'number': 16, 'output_data_dir': 'SSC-ABSTRACT-16/', 'data_ref': 'SSC-ABSTRACT-16', 'id_line_str': '# ::id SSC-ABSTRACT-16\n', 'sentence': 'In addition to these two regions, various other small-body populations, including comets, centaurs and interplanetary dust clouds, freely travel between regions.', 'graph': ''}
+- DEBUG - *** sentence 17 ***
+{'base_ref': 'SSC-ABSTRACT-17', 'number': 17, 'output_data_dir': 'SSC-ABSTRACT-17/', 'data_ref': 'SSC-ABSTRACT-17', 'id_line_str': '# ::id SSC-ABSTRACT-17\n', 'sentence': 'Six of the planets, the six largest possible dwarf planets, and many of the smaller bodies are orbited by natural satellites, usually termed "moons" after the Moon.', 'graph': ''}
+- DEBUG - *** sentence 18 ***
+{'base_ref': 'SSC-ABSTRACT-18', 'number': 18, 'output_data_dir': 'SSC-ABSTRACT-18/', 'data_ref': 'SSC-ABSTRACT-18', 'id_line_str': '# ::id SSC-ABSTRACT-18\n', 'sentence': 'Each of the outer planets is encircled by planetary rings of dust and other small objects.', 'graph': ''}
+- DEBUG - *** sentence 19 ***
+{'base_ref': 'SSC-ABSTRACT-19', 'number': 19, 'output_data_dir': 'SSC-ABSTRACT-19/', 'data_ref': 'SSC-ABSTRACT-19', 'id_line_str': '# ::id SSC-ABSTRACT-19\n', 'sentence': 'The solar wind, a stream of charged particles flowing outwards from the Sun, creates a bubble-like region in the interstellar medium known as the heliosphere.', 'graph': ''}
+- DEBUG - *** sentence 20 ***
+{'base_ref': 'SSC-ABSTRACT-20', 'number': 20, 'output_data_dir': 'SSC-ABSTRACT-20/', 'data_ref': 'SSC-ABSTRACT-20', 'id_line_str': '# ::id SSC-ABSTRACT-20\n', 'sentence': 'The heliopause is the point at which pressure from the solar wind is equal to the opposing pressure of the interstellar medium; it extends out to the edge of the scattered disc.', 'graph': ''}
+- DEBUG - *** sentence 21 ***
+{'base_ref': 'SSC-ABSTRACT-21', 'number': 21, 'output_data_dir': 'SSC-ABSTRACT-21/', 'data_ref': 'SSC-ABSTRACT-21', 'id_line_str': '# ::id SSC-ABSTRACT-21\n', 'sentence': 'The Oort cloud, which is thought to be the source for long-period comets, may also exist at a distance roughly a thousand times further than the heliosphere.', 'graph': ''}
+- DEBUG - *** sentence 22 ***
+{'base_ref': 'SSC-ABSTRACT-22', 'number': 22, 'output_data_dir': 'SSC-ABSTRACT-22/', 'data_ref': 'SSC-ABSTRACT-22', 'id_line_str': '# ::id SSC-ABSTRACT-22\n', 'sentence': 'The Solar System is located 26,000 light-years from the center of the Milky Way galaxy in the Orion Arm, which contains most of the visible stars in the night sky.', 'graph': ''}
+- DEBUG - *** sentence 23 ***
+{'base_ref': 'SSC-ABSTRACT-23', 'number': 23, 'output_data_dir': 'SSC-ABSTRACT-23/', 'data_ref': 'SSC-ABSTRACT-23', 'id_line_str': '# ::id SSC-ABSTRACT-23\n', 'sentence': 'The nearest stars are within the so-called Local Bubble, with the closest, Proxima Centauri, at 4.25 light-years.', 'graph': ''}
+- INFO - ----- number of sentences: 23
- DEBUG - -- Making output directory tree (/home/lamenji/Workspace/Tetras/amrbatch/tests/output/Test-20230303/)
- DEBUG - -- Generating sentence file
- INFO -
@@ -20,29 +62,3 @@
- DEBUG - (/home/lamenji/Workspace/Tetras/amrbatch/tests/../amr_models/model_parse_xfm_bart_large-v0_1_0)
- DEBUG - -- working directory: /home/lamenji/Workspace/Tetras/amrbatch/amrbatch/amrld/wk/
- INFO - -- Loading AMR model
-- INFO - -- Converting sentences to AMR graphs
-- INFO - ----- Sentence 1 successfully processed
-- DEBUG - ['# ::snt The sun is a star.\n(s / star\n :domain (s2 / sun))']
-- INFO - ----- Sentence 2 successfully processed
-- DEBUG - ['# ::snt Earth is a planet.\n(p / planet\n :domain p\n :name (n / name\n :op1 "Earth"))']
-- INFO - ----- Total processed graph number: 2
-- INFO - -- Generating AMR graph files
-- DEBUG - ----- AMR Graph file (penman): test-01.stog.amr.penman
-- DEBUG - ----- AMR Graph file (dot): test-01.stog.amr.dot
-- DEBUG - ----- AMR Graph file (png): {os.path.basename(good_png_fn)}
-- DEBUG - ----- AMR Graph file (penman): test-02.stog.amr.penman
-- DEBUG - ----- AMR Graph file (dot): test-02.stog.amr.dot
-- DEBUG - ----- AMR Graph file (png): {os.path.basename(good_png_fn)}
-- INFO -
- === AMR Graphs Serialization to AMR-RDF Representation ===
-- INFO - -- library: amrlk
-- INFO - -- Serialize AMR graphs to RDF using amr-ld library
-- DEBUG - ----- penman filepath: /home/lamenji/Workspace/Tetras/amrbatch/tests/output/Test-20230303/test-01/test-01.stog.amr.penman
-- DEBUG - ----- AMRLD filepath: /home/lamenji/Workspace/Tetras/amrbatch/amrbatch/amrld/wk/test-01.stog.amr.penman
-- INFO - -- Generating AMR RDF file (triple): test-01.stog.amr.nt
-- INFO - -- Generating AMR RDF file (turtle): test-01.stog.amr.ttl
-- INFO - -- Serialize AMR graphs to RDF using amr-ld library
-- DEBUG - ----- penman filepath: /home/lamenji/Workspace/Tetras/amrbatch/tests/output/Test-20230303/test-02/test-02.stog.amr.penman
-- DEBUG - ----- AMRLD filepath: /home/lamenji/Workspace/Tetras/amrbatch/amrbatch/amrld/wk/test-02.stog.amr.penman
-- INFO - -- Generating AMR RDF file (triple): test-02.stog.amr.nt
-- INFO - -- Generating AMR RDF file (turtle): test-02.stog.amr.ttl
diff --git a/tests/output/SSC-ABSTRACT-01.sentence.txt b/tests/output/SSC-ABSTRACT-01.sentence.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3a243308a2d684c15e4601d3cc102bd6661cde39
--- /dev/null
+++ b/tests/output/SSC-ABSTRACT-01.sentence.txt
@@ -0,0 +1,10 @@
+The Solar System is the gravitationally bound system of the Sun and the objects that orbit it, either directly or indirectly
+Of the objects that orbit the Sun directly, the largest are the eight planets, with the remainder being smaller objects, the dwarf planets and small Solar System bodies
+Of the objects that orbit the Sun indirectly—the natural satellites—two are larger than the smallest planet, Mercury, and one more almost equals it in size
+The Solar System formed 4.6 billion years ago from the gravitational collapse of a giant interstellar molecular cloud
+The vast majority of the system's mass is in the Sun, with the majority of the remaining mass contained in Jupiter
+The four smaller inner system planets, Mercury, Venus, Earth and Mars, are terrestrial planets, being primarily composed of rock and metal
+The four outer system planets are giant planets, being substantially more massive than the terrestrials
+The two largest planets, Jupiter and Saturn, are gas giants, being composed mainly of hydrogen and helium; the two outermost planets, Uranus and Neptune, are ice giants, being composed mostly of substances with relatively high melting points compared with hydrogen and helium, called volatiles, such as water, ammonia and methane
+All eight planets have almost circular orbits that lie within a nearly flat disc called the ecliptic
+The Solar System also contains smaller objects
\ No newline at end of file
diff --git a/tests/output/SSC-ABSTRACT-02.sentence.txt b/tests/output/SSC-ABSTRACT-02.sentence.txt
new file mode 100644
index 0000000000000000000000000000000000000000..725d070342e52f280139bc3c11815b73dfffb130
--- /dev/null
+++ b/tests/output/SSC-ABSTRACT-02.sentence.txt
@@ -0,0 +1,10 @@
+The asteroid belt, which lies between the orbits of Mars and Jupiter, mostly contains objects composed, like the terrestrial planets, of rock and metal
+Beyond Neptune's orbit lie the Kuiper belt and scattered disc, which are populations of trans-Neptunian objects composed mostly of ices, and beyond them a newly discovered population of sednoids
+Within these populations, some objects are large enough to have rounded under their own gravity, though there is considerable debate as to how many there will prove to be
+Such objects are categorized as dwarf planets
+Astronomers generally accept at least nine objects as dwarf planets: the asteroid Ceres and the trans-Neptunian objects Pluto, Eris, Haumea, Makemake, Gonggong, Quaoar, Sedna, and Orcus
+In addition to these two regions, various other small-body populations, including comets, centaurs and interplanetary dust clouds, freely travel between regions
+Six of the planets, the six largest possible dwarf planets, and many of the smaller bodies are orbited by natural satellites, usually termed "moons" after the Moon
+Each of the outer planets is encircled by planetary rings of dust and other small objects
+The solar wind, a stream of charged particles flowing outwards from the Sun, creates a bubble-like region in the interstellar medium known as the heliosphere
+The heliopause is the point at which pressure from the solar wind is equal to the opposing pressure of the interstellar medium; it extends out to the edge of the scattered disc
\ No newline at end of file
diff --git a/tests/output/SSC-ABSTRACT-03.sentence.txt b/tests/output/SSC-ABSTRACT-03.sentence.txt
new file mode 100644
index 0000000000000000000000000000000000000000..4cf2c2b7f0c4627e217bd9fdf993b24745475cc8
--- /dev/null
+++ b/tests/output/SSC-ABSTRACT-03.sentence.txt
@@ -0,0 +1,3 @@
+The Oort cloud, which is thought to be the source for long-period comets, may also exist at a distance roughly a thousand times further than the heliosphere
+The Solar System is located 26,000 light-years from the center of the Milky Way galaxy in the Orion Arm, which contains most of the visible stars in the night sky
+The nearest stars are within the so-called Local Bubble, with the closest, Proxima Centauri, at 4.25 light-years
\ No newline at end of file
diff --git a/tests/output/Test-20230303/SSC-ABSTRACT.sentence.txt b/tests/output/Test-20230303/SSC-ABSTRACT.sentence.txt
new file mode 100644
index 0000000000000000000000000000000000000000..ebee7931f8b5580f503354289f1409536959c694
--- /dev/null
+++ b/tests/output/Test-20230303/SSC-ABSTRACT.sentence.txt
@@ -0,0 +1,23 @@
+The Solar System is the gravitationally bound system of the Sun and the objects that orbit it, either directly or indirectly.
+Of the objects that orbit the Sun directly, the largest are the eight planets, with the remainder being smaller objects, the dwarf planets and small Solar System bodies.
+Of the objects that orbit the Sun indirectly—the natural satellites—two are larger than the smallest planet, Mercury, and one more almost equals it in size.
+The Solar System formed 4.6 billion years ago from the gravitational collapse of a giant interstellar molecular cloud.
+The vast majority of the system's mass is in the Sun, with the majority of the remaining mass contained in Jupiter.
+The four smaller inner system planets, Mercury, Venus, Earth and Mars, are terrestrial planets, being primarily composed of rock and metal.
+The four outer system planets are giant planets, being substantially more massive than the terrestrials.
+The two largest planets, Jupiter and Saturn, are gas giants, being composed mainly of hydrogen and helium; the two outermost planets, Uranus and Neptune, are ice giants, being composed mostly of substances with relatively high melting points compared with hydrogen and helium, called volatiles, such as water, ammonia and methane.
+All eight planets have almost circular orbits that lie within a nearly flat disc called the ecliptic.
+The Solar System also contains smaller objects.
+The asteroid belt, which lies between the orbits of Mars and Jupiter, mostly contains objects composed, like the terrestrial planets, of rock and metal.
+Beyond Neptune's orbit lie the Kuiper belt and scattered disc, which are populations of trans-Neptunian objects composed mostly of ices, and beyond them a newly discovered population of sednoids.
+Within these populations, some objects are large enough to have rounded under their own gravity, though there is considerable debate as to how many there will prove to be.
+Such objects are categorized as dwarf planets.
+Astronomers generally accept at least nine objects as dwarf planets: the asteroid Ceres and the trans-Neptunian objects Pluto, Eris, Haumea, Makemake, Gonggong, Quaoar, Sedna, and Orcus.
+In addition to these two regions, various other small-body populations, including comets, centaurs and interplanetary dust clouds, freely travel between regions.
+Six of the planets, the six largest possible dwarf planets, and many of the smaller bodies are orbited by natural satellites, usually termed "moons" after the Moon.
+Each of the outer planets is encircled by planetary rings of dust and other small objects.
+The solar wind, a stream of charged particles flowing outwards from the Sun, creates a bubble-like region in the interstellar medium known as the heliosphere.
+The heliopause is the point at which pressure from the solar wind is equal to the opposing pressure of the interstellar medium; it extends out to the edge of the scattered disc.
+The Oort cloud, which is thought to be the source for long-period comets, may also exist at a distance roughly a thousand times further than the heliosphere.
+The Solar System is located 26,000 light-years from the center of the Milky Way galaxy in the Orion Arm, which contains most of the visible stars in the night sky.
+The nearest stars are within the so-called Local Bubble, with the closest, Proxima Centauri, at 4.25 light-years.
\ No newline at end of file
diff --git a/tests/output/test-1.sentence.txt b/tests/output/test-1.sentence.txt
new file mode 100644
index 0000000000000000000000000000000000000000..57654ef993ab2f4626acadb751b820023284f27e
--- /dev/null
+++ b/tests/output/test-1.sentence.txt
@@ -0,0 +1,2 @@
+The sun is a star
+Earth is a planet.
diff --git a/tests/test_amrbatch_main.py b/tests/test_amrbatch_main.py
index e6e268491ffdfa98ec6ba3d6770bb54788a15997..4b92f612a5d01633cf3858ab1b0468a6aae58ee3 100644
--- a/tests/test_amrbatch_main.py
+++ b/tests/test_amrbatch_main.py
@@ -16,6 +16,7 @@ OUTPUT_DIR_PATH = f'{TESTS_PATH}/output/'
AMR_MODEL_PATH = f'{TESTS_PATH}/../amr_models/model_parse_xfm_bart_large-v0_1_0'
from context import amrbatch
+from utility import file_cutter
@@ -25,6 +26,7 @@ from context import amrbatch
# -- Input Data
input_filename = f'test.txt'
+input_filename = f'SSC-ABSTRACT.txt'
input_filepath = f'{INPUT_DIR_PATH}{input_filename}'
@@ -38,6 +40,13 @@ turtle_output_file = f'{base_output_name}.ttl'
+#==============================================================================
+# Cuttinf file if useful using
+#==============================================================================
+
+# file_cutter.cut_file_into_several_files(input_filepath, 10, output_dirpath=f'{OUTPUT_DIR_PATH}')
+
+
#==============================================================================
# Parsing using amrbatch main method
#==============================================================================
diff --git a/tests/utility/__init__.py b/tests/utility/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..8d1c8b69c3fce7bea45c73efd06983e3c419a92f
--- /dev/null
+++ b/tests/utility/__init__.py
@@ -0,0 +1 @@
+
diff --git a/tests/utility/file_cutter.py b/tests/utility/file_cutter.py
new file mode 100644
index 0000000000000000000000000000000000000000..76c85664a7b5f94f24380ebda03d295186d553e5
--- /dev/null
+++ b/tests/utility/file_cutter.py
@@ -0,0 +1,107 @@
+#!/usr/bin/python3.10
+# -*-coding:Utf-8 -*
+
+#==============================================================================
+# C.M. Tool: cut a file into several files
+#------------------------------------------------------------------------------
+# Script to cut a file with a lot of sentences into several files with less
+# sentences
+#==============================================================================
+
+import os, sys, re
+
+SENTENCE_SUFFIX = ".sentence.txt"
+
+
+
+#==============================================================================
+# Functions to manage in-process data
+#==============================================================================
+
+def get_sentence_output_filepath(output_dirpath, data_ref, file_number, digits):
+ file_number_str = str(file_number).rjust(digits,"0")
+ data_filename = f'{data_ref}-{file_number_str}{SENTENCE_SUFFIX}'
+ return f'{output_dirpath}{data_filename}'
+
+
+def is_valid_sentence(sentence):
+ """ True if the sentence is correct.
+ """
+ is_empty = ((sentence == "") | (sentence == "\n"))
+ lang_mark_re = re.compile("\([a-z]+\)(.)*")
+ is_language_mark = lang_mark_re.match(sentence) is not None
+ return not (is_empty | is_language_mark)
+
+
+def clean_sentence(sentence):
+ """ Sentence cleanup as needed """
+ sentence = re.sub("(\.)*\\n", "", sentence)
+ return sentence
+
+
+def __generate_new_file(new_filepath, data_list, s_number):
+ print(f'----- Generating new file: {os.path.basename(new_filepath)} ({s_number})')
+ with open(new_filepath, "w") as writing_file: # w = write
+ first = True
+ for data in data_list:
+ if not first: writing_file.write("\n")
+ writing_file.write(data)
+ first = False
+
+#==============================================================================
+# Main Method
+#==============================================================================
+
+def cut_file_into_several_files(input_filepath, split_number, output_dirpath=None):
+ print("\n" + "[AMR Batch] Cut a file into several files")
+
+ base_ref = os.path.splitext(os.path.basename(input_filepath))[0]
+ input_dirpath = os.path.dirname(input_filepath)
+ output_dirpath = output_dirpath if output_dirpath else input_dirpath
+ print("-- base_ref:", base_ref)
+ print("-- split_number:", split_number)
+ print("-- output_dirpath:", output_dirpath)
+
+ print("-- Calculating the total numbre of sentences")
+ sentence_total_number = 0
+ with open(input_filepath, "r") as reading_file: # r = read
+ for line in reading_file.readlines():
+ sentence_set = line.split(". ")
+ for sentence in sentence_set:
+ sentence_total_number += 1
+ digits_number = len(str(sentence_total_number))
+ print(f'----- total number of sentences: {sentence_total_number}')
+ print(f'----- digits number: {digits_number}')
+
+ print("-- Cut input file to several files")
+ data_list = list()
+ s_number = 0
+ f_number = 0
+ with open(input_filepath, "r") as reading_file: # r = read
+ for line in reading_file.readlines():
+
+ sentence_set = line.split(". ")
+
+ for sentence in sentence_set:
+ if s_number == split_number:
+ s_number = 0
+ data_list.clear()
+ if is_valid_sentence(sentence):
+ s_number += 1
+ data_list.append(sentence)
+ else:
+ print(f'----- invalid sentence: {sentence}')
+ if s_number == split_number:
+ f_number += 1
+ new_filepath = get_sentence_output_filepath(
+ output_dirpath, base_ref, f_number, digits_number)
+ __generate_new_file(new_filepath, data_list, s_number)
+
+ if len(data_list) > 0:
+ f_number += 1
+ new_filepath = get_sentence_output_filepath(
+ output_dirpath, base_ref, f_number, digits_number)
+ __generate_new_file(new_filepath, data_list, s_number)
+
+ print(f'----- Generated file total number: {f_number}')
+
\ No newline at end of file