From ad1711115851aee7d5a5725ecd6eb25cf00d6d99 Mon Sep 17 00:00:00 2001 From: Vlad Maevski <93771100+Heliotropes@users.noreply.github.com> Date: Thu, 14 Dec 2023 21:23:31 +0300 Subject: [PATCH] Add files via upload --- .../Poland_medcine_parser-main/LICENSE | 21 +++ .../Poland_medcine_parser-main/README.md | 55 ++++++ .../Poland_medcine_parser-main/translator.py | 165 ++++++++++++++++++ 3 files changed, 241 insertions(+) create mode 100644 src/loaders/Poland_medcine_parser-main/LICENSE create mode 100644 src/loaders/Poland_medcine_parser-main/README.md create mode 100644 src/loaders/Poland_medcine_parser-main/translator.py diff --git a/src/loaders/Poland_medcine_parser-main/LICENSE b/src/loaders/Poland_medcine_parser-main/LICENSE new file mode 100644 index 0000000..b3bb770 --- /dev/null +++ b/src/loaders/Poland_medcine_parser-main/LICENSE @@ -0,0 +1,21 @@ +MIT License + +Copyright (c) 2023 Vlad Maevski + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. diff --git a/src/loaders/Poland_medcine_parser-main/README.md b/src/loaders/Poland_medcine_parser-main/README.md new file mode 100644 index 0000000..84d6423 --- /dev/null +++ b/src/loaders/Poland_medcine_parser-main/README.md @@ -0,0 +1,55 @@ +# Poland_medcine_parser + +This repository contains a Python script, translator.py, which provides functions for translating and processing medicine data from an Excel file. The script utilizes the openpyxl library for reading Excel files and the googletrans library for translating text. + +## Requirements + +To run the script, you need to have the following dependencies installed: + +- openpyxl: A library for reading and writing Excel files. + +- googletrans: A library for Google Translate API. + +You can install these dependencies using the following command: + +pip install openpyxl googletrans +## Usage + +1. Clone the repository to your local machine. + +2. Install the required dependencies as mentioned above. + +3. Open the translator.py file in a text editor. + +4. Modify the excel_file variable to specify the path to your Excel file containing medicine data. + +5. Adjust the number_of_files and number_of_scs variables according to your desired configuration. + +6. Run the script using the following command: + +python translator.py +The script will parse the medicine data from the Excel file, translate relevant information to English, and generate multiple .scs files based on the specified configuration. + +## File Structure + +The script generates multiple .scs files, each containing the translated and processed medicine data. The number of files and the number of records per file are determined by the number_of_files and number_of_scs variables, respectively. + +## Translation and Processing + +The script performs the following translation and processing tasks: + +- Translates medicine names and other text fields from Polish to English using the Google Translate API. + +- Fixes and standardizes various fields, such as medicine names, dosages, alternative names, pharmaceutical forms, and routes of administration. + +- Extracts information such as ATC codes, marketing authorization holders, active substances, countries of sale, and dosage forms. + +- Generates a template for each medicine record in the form of an .scs file, following a specific structure. + +## Note + +Please note that the script relies on the Google Translate API for translation. Make sure to comply with the terms of service and usage limits of the API to avoid any issues. + +## License + +This project is licensed under the [MIT License](LICENSE). Feel free to modify and distribute the code as per the terms of the license. diff --git a/src/loaders/Poland_medcine_parser-main/translator.py b/src/loaders/Poland_medcine_parser-main/translator.py new file mode 100644 index 0000000..20bb754 --- /dev/null +++ b/src/loaders/Poland_medcine_parser-main/translator.py @@ -0,0 +1,165 @@ +import openpyxl +from googletrans import Translator + + +def translator(text, lang): + ts= Translator() + T = ts.translate(text, dest = lang) + return T.text + +def fix_name(name): + name = name.replace(" ","_") + return name + +def fix_dose(dose): + if dose == '-': + result = ["",""] + return result + dose = dose.replace(",",".") + dose = dose.replace(" ","") + dose = dose.replace("(","") + dose = dose.replace('niemniejniż','') + if 'mg' in dose or 'mcg' in dose: + dose = dose[0:dose.find('g')+1] + elif 'j.m.' in dose: + dose = dose[0:dose.find('j.m.')+1] + dose = dose.replace(".","") + dose1 = "_" + dose + dose2 = "(" + dose + ")" + result = [dose1,dose2] + return result + +def fix_P_name(P_name, name): + if '+' in P_name: + result = "" + sp = P_name.split(sep = '+') + for n in sp: + result = result + "[" + result = result + n + "]; " + else: result = '['+ P_name +'];' + if P_name == '-': + result = name + ';' + return result + + +def fix_atc(atc): + if atc == '': + return '' + else: + return '=> nrel_atc_code: ' + atc + ';' + +def fix_country(country): + sp = country.split() + st = set(sp) + result = "" + for n in st: + result = result + n + "; " + return result + +def fix_active(active): + if '+' in active: + result = "" + sp = active.split(sep = '+') + for n in sp: + n = n.replace(" ","_") + for n in sp: + result = result + "[" + result = result + n + "]; " + else: + result = '[' + active + "];" + return result + +def fix_dosage_form(dosage_form): + dosage_form = dosage_form.replace("/","") + dosage_form = dosage_form.replace(" ","_") + dosage_form = dosage_form.replace(",","") + return dosage_form + +def fix_route(dosage_form): + result = "" + dosage_form_low = dosage_form.lower() + if 'injection' in dosage_form_low or 'infusion' in dosage_form_low: + result = 'concept_parenteral_route;;' + if 'cream' in dosage_form_low or 'gel'in dosage_form_low or 'transdermal' in dosage_form_low: + result = 'concept_transdermal_route;;' + if 'drops' in dosage_form_low or 'eyes'in dosage_form_low: + result = 'concept_intra_ocular_route;;' + if 'capsules' in dosage_form_low or 'pills' in dosage_form_low or 'tablets' in dosage_form_low: + result = 'concept_oral_route;;' + if result != "": + result = '=> nrel_route_of_administration:' + result + return result + +def create_file(templates, c_files, c_scs): + count = 0 + for i in range(c_files): + file = open(f"{i}.scs","a+",encoding="utf-8") + for j in range(c_scs): + count+=1 + file.write(templates[count]) + file.close() + +def parse_and_input(excel_file, number_of_files, number_of_scs): + workbook = openpyxl.open(excel_file, read_only = True) + sheet = workbook.active + templates = [] + for row in range(2,number_of_scs * number_of_files + 1): + name_pl = sheet[row][1].value + name_en = translator(name_pl, 'en') + dose0 = sheet[row][4].value + ATC = sheet[row][6].value + ATC = fix_atc(ATC) + P_name0 = sheet[row][2].value + company = translator(sheet[row][7].value, 'en') + dosage_form0 = translator(sheet[row][5].value, 'en') + + country_test = sheet[row][10].value + if country_test == "": + country_test = "Polska" + country0 = translator(country_test, 'en') + + name = fix_name(name_en).lower().replace('%','') + dose = fix_dose(dose0) + dose1 = dose[0] + dose2 = dose[1] + P_name = fix_P_name(P_name0, name_en) + + active_test = sheet[row][8].value + if active_test == "": + active_test = P_name + active0 = translator(active_test, 'en') + + active = fix_active(active0) + country = fix_country(country0) + dosage_form = fix_dosage_form(dosage_form0) + route = fix_route(dosage_form0) + end ='' + if route == "": + end = ';' + + template = f""" +medication_{name}{dose1} +<-sc_node_not_relation; +=> nrel_main_idtf: + [{name_en} {dose2}] (* <- lang_en;;*); + [{name_pl} {dose2}] (* <- lang_pl;;*); +{ATC} +=> nrel_international_non_proprietary_name: {P_name} +=> nrel_company: [{company}]; +=> nrel_countries_of_sale: {country} +=> nrel_active_substances: {active} +=> nrel_dosage_form:{dosage_form};{end} +{route} + """ + templates.append(template) + create_file(templates, number_of_files, number_of_scs) + + +excel_file = 'C:\work\Course\Med.xlsx' +values = parse_and_input(excel_file, 5, 10) + + + + + +