From d77cb041abd40332e494fafe416e9ebed0717678 Mon Sep 17 00:00:00 2001 From: Mike Jones Date: Fri, 26 Feb 2021 08:53:56 +0000 Subject: [PATCH] first commit for public release --- .gitignore | 53 ++++++++++ LICENSE.txt | 202 ++++++++++++++++++++++++++++++++++++ README.md | 51 +++++++++ process_xml.py | 264 +++++++++++++++++++++++++++++++++++++++++++++++ requirements.txt | 5 + 5 files changed, 575 insertions(+) create mode 100644 .gitignore create mode 100644 LICENSE.txt create mode 100644 README.md create mode 100644 process_xml.py create mode 100644 requirements.txt diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..b12d0e3 --- /dev/null +++ b/.gitignore @@ -0,0 +1,53 @@ +# These are some examples of commonly ignored file patterns. +# You should customize this list as applicable to your project. +# Learn more about .gitignore: +# https://www.atlassian.com/git/tutorials/saving-changes/gitignore + +# Node artifact files +node_modules/ +dist/ + +# Compiled Java class files +*.class + +# Compiled Python bytecode +*.py[cod] + +# Log files +*.log + +# Package files +*.jar + +# Maven +target/ +dist/ + +# JetBrains IDE +.idea/ + +# Unit test reports +TEST*.xml + +# Generated by MacOS +.DS_Store + +# Generated by Windows +Thumbs.db + +# Applications +*.app +*.exe +*.war + +# Large media files +*.mp4 +*.tiff +*.avi +*.flv +*.mov +*.wmv + +input/ +output/ +sample/*.xml diff --git a/LICENSE.txt b/LICENSE.txt new file mode 100644 index 0000000..a2e6a6f --- /dev/null +++ b/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright 2021 University of Bristol + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..50dcd64 --- /dev/null +++ b/README.md @@ -0,0 +1,51 @@ +## Introduction + +A Python script to process XML files created by the 'Qualitivity' plugin for Trados Studio. The script creates CSV file(s) with details of the language translation process including keystroke counts, count and duration of pauses in typing, and the duration of 'Records' or segment visits. + +The script uses pandas (https://pandas.pydata.org/) for the creation of the CSV file and NumPy (https://numpy.org/) for date parsing and the calculations of milliseconds. + +## Setup + +Setup a virtual environment: + + ``` + python3 -m venv venv + source venv/bin/activate + ``` + +Install libraries used by the script: + + ``` + pip install --upgrade pip + pip install -r requirements.txt + ``` + +If running on Windows, see https://docs.python.org/3/tutorial/venv.html + +## Running the script + +The scripts take two arguments: a directory of the input XML files and a directory for the output files. The script will create the output directory if needed. + +The following will create two files for each input XML file. One file will hold the duration and count values for each 'Record' in the source XML. The second is an 'audit' file providing each interval between keystrokes without categorisation. The 'audit' includes information about any 'system keystrokes' omitted from the main output files. These are keystroke logs generated by Trados Studio (e.g. when a segment is automatically populated with a machine translation match). + + ``` + python process_xml.py ./sample ./output + ``` + +It is possible to combine the results, so we only have two files: 'combined.csv' and 'combined-audit.csv'. The first has the duration and count values and the second provides the 'audit'. The combined files have an additional column – 'File' – that indicates the source XML file. + + ``` + python process_xml.py ./sample ./output --combine + ``` +## Translation process measures + +The features for each 'Record' in the Qualitivity XML files are as follows. All pause measures are provided based on three minimum pause duration thresholds: 300 milliseconds and above (\_300), 500 milliseconds and above (\_500), and 1 second and above (\_1s). + +* Record ID: The ID for each 'Record' in the Qualitivity output +* Segment ID: The ID for each text segment +* Total pause duration: The total duration of pauses - milliseconds. +* Pause count: The number of pauses - count. +* Keystrokes: The number of keystrokes ('ks created' elements) - count. +* Active ms: The duration of each 'Record' copied from the 'activeMiliseconds' attribute in the Qualitivity XML file - milliseconds. +* Record duration: The duration of each 'Record' computed as the difference between 'stopped' and 'started' times for the record - milliseconds. +* Total duration: Same as Record duration, obtained by adding up all intervals in between keystrokes or beginning/end of a record. diff --git a/process_xml.py b/process_xml.py new file mode 100644 index 0000000..c8f8f74 --- /dev/null +++ b/process_xml.py @@ -0,0 +1,264 @@ +""" +A script that processes the Qualitivity XML files and creates CSV files of extracted data. +""" + +import argparse +import os +import sys +from xml.etree import ElementTree + +import numpy as np +import pandas as pd + +# data frame columns +columns = ['Record ID', 'Segment ID', 'Total pause duration_300', 'Pause count_300', + 'Total pause duration_500', 'Pause count_500', 'Total pause duration_1s', 'Pause count_1s', + 'Keystrokes', 'Active ms', 'Record duration', 'Total duration'] + +# date time format used in the XML +DATE_TIME_FORMAT = '%Y-%m-%dT%H:%M:%S.%f' + + +def normalize_attribute(root): + """ Make all the attributes lower case since the source XML files are not consistent. """ + for attr, value in root.attrib.items(): + norm_attr = attr.lower() + if norm_attr != attr: + root.set(norm_attr, value) + root.attrib.pop(attr) + + for child in root: + normalize_attribute(child) + + +def create_pause_counts_dict(): + """ Dictionary that will hold our pause count and duration value for a element in the XML.""" + return { + 'duration_300': 0, + 'count_300': 0, + 'duration_500': 0, + 'count_500': 0, + 'duration_1000': 0, + 'count_1000': 0, + 'total_pause_ms': 0, + 'total_duration': 0 + } + + +def ms(val): + """ Turn a float value into milliseconds as an integer. """ + return int(val * 1000) + + +def categorize_pause(counts, pause_ms): + """ + The method that updates the count and duration values. + :param counts: the dict that holds our pause count and duration values. + :param pause_ms: the pause in milliseconds + :return: None. + """ + if pause_ms >= 300: + counts['duration_300'] += pause_ms + counts['count_300'] += 1 + + if pause_ms >= 500: + counts['duration_500'] += pause_ms + counts['count_500'] += 1 + + if pause_ms >= 1000: + counts['duration_1000'] += pause_ms + counts['count_1000'] += 1 + + counts['total_duration'] += pause_ms + + +def valid_keystroke(keystroke): + """ Are we dealing with a valid keystroke? False if its a 'system' keystroke. """ + if keystroke.attrib['origin'] and keystroke.attrib['system'] and not keystroke.attrib['key']: + return False + elif not keystroke.attrib['selection'] and not keystroke.attrib['text'] and not keystroke.attrib['key'] and \ + keystroke.attrib['shift'] == 'False' and keystroke.attrib['ctrl'] == 'False' \ + and keystroke.attrib['alt'] == 'False': + return False + else: + return True + + +def process_file(xml_input): + """ + The method that updates the count and duration values. + :param xml_input: the XML file to be processes. + :return: a pandas data frame of data extracted from the xml. + """ + # empty data structure for the data + categorized_data = [] + + # keep track of all pauses + all_pauses_data = [] + + if not os.path.isfile(xml_input): + raise ValueError('{} is not a file'.format(xml_input)) + + # parse the document and get the root element + doc_tree = ElementTree.parse(xml_input) + root = doc_tree.getroot() + + # make attributes lower case - source XML not consistent + normalize_attribute(root) + + # find all the elements + records = root.findall('.//Document/Record') + + # go through the records, each will be a row in the CVS file + for record in records: + + # get the date/time that the record data started + record_started = record.attrib['started'] + record_started_dt = np.datetime64(record_started) + + # get the date/time that the record data stopped + record_ended = record.attrib['stopped'] + record_ended_dt = np.datetime64(record_ended) + + # calculate the duration of the work on the record in milliseconds + duration_dt = record_ended_dt - record_started_dt + duration_ms = duration_dt.astype(int) + + # we track 'milestones', i.e. where the last operation ended + last_milestone = record_started_dt + + # values we want from the attribute + record_id = record.attrib['id'] + segment_id = record.attrib['segmentid'] + active_ms = record.attrib['activemiliseconds'] + + # calculate pauses + pause_counts = create_pause_counts_dict() + + # get all the keystrokes for a record + keystrokes = record.findall('.//ks') + + # count all the keystrokes + keystrokes_count = len(keystrokes) + + valid_keystroke_count = 0 + + if keystrokes_count == 0: + categorize_pause(pause_counts, duration_ms) + all_pauses_data.append([record_id, segment_id, duration_ms, 'No ks']) + elif keystrokes_count == 1 and not valid_keystroke(keystrokes[0]): + categorize_pause(pause_counts, duration_ms) + all_pauses_data.append([record_id, segment_id, duration_ms, '1 system ks omitted']) + keystrokes_count = 0 + else: + # iterate over the keystrokes to calculate pauses + for ks in keystrokes: + # filter out 'system' keystrokes + if valid_keystroke(ks): + # keep track of valid keystrokes + valid_keystroke_count += 1 + created = ks.attrib['created'] + created_dt = np.datetime64(created) + diff = created_dt - last_milestone + diff_ms = diff.astype(int) + last_milestone = created_dt + # categorise + categorize_pause(pause_counts, diff_ms) + # not categorised, for the audit + all_pauses_data.append([record_id, segment_id, diff_ms, '']) + else: + all_pauses_data.append([record_id, segment_id, None, 'Omitted ks']) + + if valid_keystroke_count > 0: + # calculate the pause between the last keystroke and when the record stopped. + last_pause_dt = record_ended_dt - last_milestone + last_pause_ms = last_pause_dt.astype(int) + categorize_pause(pause_counts, last_pause_ms) + all_pauses_data.append([record_id, segment_id, last_pause_ms, '']) + keystrokes_count = valid_keystroke_count + + # create a row of data + row = [record_id, segment_id, pause_counts['duration_300'], pause_counts['count_300'], + pause_counts['duration_500'], pause_counts['count_500'], pause_counts['duration_1000'], + pause_counts['count_1000'], keystrokes_count, active_ms, duration_ms, + pause_counts['total_duration']] + + # append to 2d array + categorized_data.append(row) + + # create pandas data frames + df = pd.DataFrame(data=categorized_data, columns=columns) + all_df = pd.DataFrame(data=all_pauses_data, columns=['Record ID', 'Segment ID', 'Pause durations', 'Notes']) + return df, all_df + + +def process(input_dir, output_dir, combine): + """ + Process a folder of XML files and create a folder of CSV file or single file with the combined results. + :param input_dir: input directory with the source XML files. + :param output_dir output directory to save the CSV file. + :param combine boolean, (True) to combine the results, and (False) to create separate CSV files + for each XML files. + :return: a pandas data frame of data extracted from the xml. + """ + + # holds data frames if we are combining + # into a single output file + combine_df = [] + all_data_combined_df = [] + omitted_combined_df = [] + + # check we have an input folder + if not os.path.isdir(input_dir): + print('Input is not a folder. Exiting') + sys.exit(1) + + # check we have an output folder + if not os.path.isdir(output_dir): + print('Output is not a folder, creating it.') + os.makedirs(output_dir) + + # walk the directory looking for files + for root, dirs, files in os.walk(input_dir): + # iterate the files + for file in files: + # we are interested in xml files + if file.endswith('.xml'): + # process the file and create a data frame + input_file = os.path.join(root, file) + df, all_df = process_file(input_file) + # if we are combining, we want the filename in the data (first column). + # add the data frame to our temporary array + if combine: + df.insert(0, 'File', file) + all_df.insert(0, 'File', file) + combine_df.append(df) + all_data_combined_df.append(all_df) + else: + # not combining, so create a CSV file for each xml file + output_file = os.path.join(output_dir, file.replace('.xml', '.csv')) + all_output_file = os.path.join(output_dir, file.replace('.xml', '-audit.csv')) + df.to_csv(output_file, index=False) + all_df.to_csv(all_output_file, index=False) + + # if we are combining, combine output into two files + if combine: + df = pd.concat(combine_df, ignore_index=True) + df.to_csv(os.path.join(output_dir, 'combined.csv'), index=False) + all_df = pd.concat(all_data_combined_df, ignore_index=True) + all_df.to_csv(os.path.join(output_dir, 'combined-audit.csv'), index=False) + + +if __name__ == "__main__": + """ Main method that will get arguments on the command line. """ + + # define the command line parameters and switches + parser = argparse.ArgumentParser(description='Process Qualitivity XML files.') + parser.add_argument('input', type=str, help='folder with the source XML files') + parser.add_argument('output', type=str, help='folder for the output CSV files') + parser.add_argument('--combine', required=False, action='store_true', + help='Combine the output into a single CSV file') + + # parse and process + args = parser.parse_args() + process(args.input, args.output, args.combine) diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..f763216 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,5 @@ +numpy==1.19.2 +pandas==1.1.3 +python-dateutil==2.8.1 +pytz==2020.1 +six==1.15.0