From 357ca458695fbc60c97de3d1cdf89034a8722bc5 Mon Sep 17 00:00:00 2001 From: BonfaceKilz Date: Thu, 27 Aug 2020 01:18:11 +0300 Subject: Replace "string.split" & "string.join" with python's inbuilt methods --- scripts/maintenance/readProbeSetMean_v7.py | 20 ++++++++++---------- scripts/maintenance/readProbeSetSE_v7.py | 14 +++++++------- wqflask/base/data_set.py | 2 +- wqflask/base/trait.py | 14 +++++++------- wqflask/utility/webqtlUtil.py | 4 ++-- wqflask/wqflask/external_tools/send_to_geneweaver.py | 2 +- wqflask/wqflask/external_tools/send_to_webgestalt.py | 2 +- wqflask/wqflask/interval_analyst/GeneUtil.py | 4 ++-- .../marker_regression/display_mapping_results.py | 2 +- wqflask/wqflask/marker_regression/plink_mapping.py | 6 +++--- wqflask/wqflask/show_trait/show_trait.py | 4 ++-- wqflask/wqflask/snp_browser/snp_browser.py | 12 ++++++------ 12 files changed, 43 insertions(+), 43 deletions(-) diff --git a/scripts/maintenance/readProbeSetMean_v7.py b/scripts/maintenance/readProbeSetMean_v7.py index a540796a..43f084f4 100755 --- a/scripts/maintenance/readProbeSetMean_v7.py +++ b/scripts/maintenance/readProbeSetMean_v7.py @@ -60,15 +60,15 @@ print('Checking if each line have same number of members') GeneList = [] isCont = 1 header = fp.readline() -header = string.split(string.strip(header), '\t') -header = list(map(string.strip, header)) +header = header.strip().split('\t') +header = [x.strip() for x in header] nfield = len(header) line = fp.readline() kj = 0 while line: - line2 = string.split(string.strip(line), '\t') - line2 = list(map(string.strip, line2)) + line2 = line.strip().split('\t') + line2 = [x.strip() for x in line2] if len(line2) != nfield: print(("Error : " + line)) isCont = 0 @@ -98,8 +98,8 @@ print('Checking if each strain exist in database') isCont = 1 fp.seek(0) header = fp.readline() -header = string.split(string.strip(header), '\t') -header = list(map(string.strip, header)) +header = header.strip().split('\t') +header = [x.strip() for x in header] header = list(map(translateAlias, header)) header = header[dataStart:] Ids = [] @@ -126,8 +126,8 @@ print('Check if each ProbeSet exist in database') ##---- find PID is name or target ----## line = fp.readline() line = fp.readline() -line2 = string.split(string.strip(line), '\t') -line2 = list(map(string.strip, line2)) +line2 = line.strip().split('\t') +line2 = [x.strip() for x in line2] PId = line2[0] db.execute('select Id from ProbeSet where Name="%s" and ChipId=%d' % @@ -222,8 +222,8 @@ kj = 0 values1 = [] values2 = [] while line: - line2 = string.split(string.strip(line), '\t') - line2 = list(map(string.strip, line2)) + line2 = line.strip().split('\t') + line2 = [x.strip() for x in line2] PId = line2[0] recordId = NameIds[PId] diff --git a/scripts/maintenance/readProbeSetSE_v7.py b/scripts/maintenance/readProbeSetSE_v7.py index 20a846a4..edd9e7b0 100755 --- a/scripts/maintenance/readProbeSetSE_v7.py +++ b/scripts/maintenance/readProbeSetSE_v7.py @@ -71,14 +71,14 @@ print('Checking if each line have same number of members') GeneList = [] isCont = 1 header = fp.readline() -header = string.split(string.strip(header), '\t') +header = header.strip().split('\t') header = list(map(string.strip, header)) nfield = len(header) line = fp.readline() kj = 0 while line: - line2 = string.split(string.strip(line), '\t') + line2 = line.strip().split('\t') line2 = list(map(string.strip, line2)) if len(line2) != nfield: isCont = 0 @@ -109,7 +109,7 @@ print('Checking if each strain exist in database') isCont = 1 fp.seek(0) header = fp.readline() -header = string.split(string.strip(header), '\t') +header = header.strip().split('\t') header = list(map(string.strip, header)) header = list(map(translateAlias, header)) header = header[dataStart:] @@ -137,8 +137,8 @@ print('Check if each ProbeSet exist in database') ##---- find PID is name or target ----## line = fp.readline() line = fp.readline() -line2 = string.split(string.strip(line), '\t') -line2 = list(map(string.strip, line2)) +line2 = line.strip().split('\t') +line2 = [x.strip() for x in line2] PId = line2[0] db.execute('select Id from ProbeSet where Name="%s" and ChipId=%d' % @@ -217,8 +217,8 @@ line = fp.readline() kj = 0 while line: - line2 = string.split(string.strip(line), '\t') - line2 = list(map(string.strip, line2)) + line2 = line.strip().split('\t') + line2 = [x.strip() for x in line2] CellId = line2[0] if CellId not in ProbeNameId: diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index 8ac7a279..ce017fb4 100644 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -697,7 +697,7 @@ class DataSet(object): else: query = "SELECT {}.Name,".format(escape(dataset_type)) data_start_pos = 1 - query += string.join(temp, ', ') + query += ', '.join(temp) query += ' FROM ({}, {}XRef, {}Freeze) '.format(*mescape(dataset_type, self.type, self.type)) diff --git a/wqflask/base/trait.py b/wqflask/base/trait.py index b20efd2a..2fd5d725 100644 --- a/wqflask/base/trait.py +++ b/wqflask/base/trait.py @@ -150,8 +150,8 @@ class GeneralTrait(object): alias = 'Not available' if getattr(self, "alias", None): - alias = string.replace(self.alias, ";", " ") - alias = string.join(string.split(alias), ", ") + alias = self.alias.replace(";", " ") + alias = ", ".join(alias.split()) return alias @@ -437,7 +437,7 @@ def retrieve_trait_info(trait, dataset, get_qtl_info=False): #XZ, 05/08/2009: We also should use Geno.Id to find marker instead of just using Geno.Name # to avoid the problem of same marker name from different species. elif dataset.type == 'Geno': - display_fields_string = string.join(dataset.display_fields, ',Geno.') + display_fields_string = ',Geno.'.join(dataset.display_fields) display_fields_string = 'Geno.' + display_fields_string query = """ SELECT %s @@ -456,8 +456,8 @@ def retrieve_trait_info(trait, dataset, get_qtl_info=False): query = """SELECT %s FROM %s WHERE Name = %s""" logger.sql(query) trait_info = g.db.execute(query, - (string.join(dataset.display_fields, ','), - dataset.type, trait.name)).fetchone() + ','.join(dataset.display_fields), + dataset.type, trait.name).fetchone() if trait_info: trait.haveinfo = True @@ -501,8 +501,8 @@ def retrieve_trait_info(trait, dataset, get_qtl_info=False): trait.pubmed_link = webqtlConfig.PUBMEDLINK_URL % trait.pubmed_id if dataset.type == 'ProbeSet' and dataset.group: - description_string = str(str(trait.description).strip(codecs.BOM_UTF8), 'utf-8') - target_string = str(str(trait.probe_target_description).strip(codecs.BOM_UTF8), 'utf-8') + description_string = trait.description + target_string = trait.probe_target_description if len(description_string) > 1 and description_string != 'None': description_display = description_string diff --git a/wqflask/utility/webqtlUtil.py b/wqflask/utility/webqtlUtil.py index d4979011..5681fadf 100644 --- a/wqflask/utility/webqtlUtil.py +++ b/wqflask/utility/webqtlUtil.py @@ -107,7 +107,7 @@ def hasAccessToConfidentialPhenotypeTrait(privilege, userName, authorized_users) if webqtlConfig.USERDICT[privilege] > webqtlConfig.USERDICT['user']: access_to_confidential_phenotype_trait = 1 else: - AuthorizedUsersList=list(map(string.strip, string.split(authorized_users, ','))) - if AuthorizedUsersList.__contains__(userName): + AuthorizedUsersList=[x.strip() for x in authorized_users.split(',')] + if userName in AuthorizedUsersList: access_to_confidential_phenotype_trait = 1 return access_to_confidential_phenotype_trait diff --git a/wqflask/wqflask/external_tools/send_to_geneweaver.py b/wqflask/wqflask/external_tools/send_to_geneweaver.py index 93164233..4c958a88 100644 --- a/wqflask/wqflask/external_tools/send_to_geneweaver.py +++ b/wqflask/wqflask/external_tools/send_to_geneweaver.py @@ -55,7 +55,7 @@ class SendToGeneWeaver(object): 'client': "genenetwork", 'species': species_name, 'idtype': self.chip_name, - 'list': string.join(trait_name_list, ","), + 'list': ",".join(trait_name_list), } def get_trait_name_list(trait_list): diff --git a/wqflask/wqflask/external_tools/send_to_webgestalt.py b/wqflask/wqflask/external_tools/send_to_webgestalt.py index b255ba95..2f068792 100644 --- a/wqflask/wqflask/external_tools/send_to_webgestalt.py +++ b/wqflask/wqflask/external_tools/send_to_webgestalt.py @@ -47,7 +47,7 @@ class SendToWebGestalt(object): id_type = "entrezgene" self.hidden_vars = { - 'gene_list' : string.join(gene_id_list, "\n"), + 'gene_list' : "\n".join(gene_id_list), 'id_type' : "entrezgene", 'ref_set' : "genome", 'enriched_database_category' : "geneontology", diff --git a/wqflask/wqflask/interval_analyst/GeneUtil.py b/wqflask/wqflask/interval_analyst/GeneUtil.py index 17c8ccbf..d0dd7aea 100644 --- a/wqflask/wqflask/interval_analyst/GeneUtil.py +++ b/wqflask/wqflask/interval_analyst/GeneUtil.py @@ -31,7 +31,7 @@ def loadGenes(chrName, diffCol, startMb, endMb, species='mouse'): Chromosome = '%s' AND ((TxStart > %f and TxStart <= %f) OR (TxEnd > %f and TxEnd <= %f)) ORDER BY txStart - """ % (string.join(fetchFields, ", "), + """ % (", ".join(fetchFields), speciesId, chrName, startMb, endMb, startMb, endMb)).fetchall() @@ -66,7 +66,7 @@ def loadGenes(chrName, diffCol, startMb, endMb, species='mouse'): othSpec, othSpecId = item newdict2 = {} - resultsOther = g.db.execute("SELECT %s FROM GeneList WHERE SpeciesId = %d AND geneSymbol= '%s' LIMIT 1" % (string.join(fetchFields, ", "), + resultsOther = g.db.execute("SELECT %s FROM GeneList WHERE SpeciesId = %d AND geneSymbol= '%s' LIMIT 1" % (", ".join(fetchFields), othSpecId, newdict["GeneSymbol"])).fetchone() diff --git a/wqflask/wqflask/marker_regression/display_mapping_results.py b/wqflask/wqflask/marker_regression/display_mapping_results.py index ccdafa14..dfaa1562 100644 --- a/wqflask/wqflask/marker_regression/display_mapping_results.py +++ b/wqflask/wqflask/marker_regression/display_mapping_results.py @@ -454,7 +454,7 @@ class DisplayMappingResults(object): Chr_Length.Name in (%s) Order by Chr_Length.OrderId - """ % (self.dataset.group.name, string.join(["'%s'" % X[0] for X in self.ChrList[1:]], ", "))) + """ % (self.dataset.group.name, ", ".join(["'%s'" % X[0] for X in self.ChrList[1:]]))) self.ChrLengthMbList = [x[0]/1000000.0 for x in self.ChrLengthMbList] self.ChrLengthMbSum = reduce(lambda x, y:x+y, self.ChrLengthMbList, 0.0) diff --git a/wqflask/wqflask/marker_regression/plink_mapping.py b/wqflask/wqflask/marker_regression/plink_mapping.py index 2f282adc..6c38c34f 100644 --- a/wqflask/wqflask/marker_regression/plink_mapping.py +++ b/wqflask/wqflask/marker_regression/plink_mapping.py @@ -83,7 +83,7 @@ def get_samples_from_ped_file(dataset): sample_list=[] while line: - lineList = string.split(string.strip(line), '\t') + lineList = line.strip().split('\t') lineList = list(map(string.strip, lineList)) sample_name = lineList[0] @@ -155,8 +155,8 @@ def parse_plink_output(output_filename, species): # output: lineList list ####################################################### def build_line_list(line=None): - line_list = string.split(string.strip(line), ' ')# irregular number of whitespaces between columns + line_list = line.strip().split(' ')# irregular number of whitespaces between columns line_list = [item for item in line_list if item !=''] line_list = list(map(string.strip, line_list)) - return line_list \ No newline at end of file + return line_list diff --git a/wqflask/wqflask/show_trait/show_trait.py b/wqflask/wqflask/show_trait/show_trait.py index e93b0289..88cd7dca 100644 --- a/wqflask/wqflask/show_trait/show_trait.py +++ b/wqflask/wqflask/show_trait/show_trait.py @@ -229,8 +229,8 @@ class ShowTrait(object): hddn = OrderedDict() if self.dataset.group.allsamples: - hddn['allsamples'] = string.join(self.dataset.group.allsamples, ' ') - hddn['primary_samples'] = string.join(self.primary_sample_names, ',') + hddn['allsamples'] = ''.join(self.dataset.group.allsamples) + hddn['primary_samples'] = ''.join(self.primary_sample_names) hddn['trait_id'] = self.trait_id hddn['trait_display_name'] = self.this_trait.display_name hddn['dataset'] = self.dataset.name diff --git a/wqflask/wqflask/snp_browser/snp_browser.py b/wqflask/wqflask/snp_browser/snp_browser.py index 0db7e1fe..2df71b12 100644 --- a/wqflask/wqflask/snp_browser/snp_browser.py +++ b/wqflask/wqflask/snp_browser/snp_browser.py @@ -456,7 +456,7 @@ class SnpBrowser(object): function_list = [] if function_details: - function_list = string.split(string.strip(function_details), ",") + function_list = function_details.strip().split(",") function_list = list(map(string.strip, function_list)) function_list[0] = function_list[0].title() function_details = ", ".join(item for item in function_list) @@ -722,11 +722,11 @@ def get_effect_details_by_category(effect_name = None, effect_value = None): new_codon_group_list = ['Start Gained'] codon_effect_group_list = ['Start Lost', 'Stop Gained', 'Stop Lost', 'Nonsynonymous', 'Synonymous'] - effect_detail_list = string.split(string.strip(effect_value), '|') + effect_detail_list = effect_value.strip().split('|') effect_detail_list = list(map(string.strip, effect_detail_list)) for index, item in enumerate(effect_detail_list): - item_list = string.split(string.strip(item), ',') + item_list = item.strip().split(',') item_list = list(map(string.strip, item_list)) gene_id = item_list[0] @@ -746,13 +746,13 @@ def get_effect_details_by_category(effect_name = None, effect_value = None): if effect_name in new_codon_group_list: new_codon = item_list[6] tmp_list = [biotype, new_codon] - function_detail_list.append(string.join(tmp_list, ", ")) + function_detail_list.append(", ".join(tmp_list)) elif effect_name in codon_effect_group_list: old_new_AA = item_list[6] old_new_codon = item_list[7] codon_num = item_list[8] tmp_list = [biotype, old_new_AA, old_new_codon, codon_num] - function_detail_list.append(string.join(tmp_list, ", ")) + function_detail_list.append(", ".join(tmp_list)) else: function_detail_list.append(biotype) @@ -852,7 +852,7 @@ def get_gene_id_name_dict(species_id, gene_name_list): if len(gene_name_list) == 0: return "" gene_name_str_list = ["'" + gene_name + "'" for gene_name in gene_name_list] - gene_name_str = string.join(gene_name_str_list, ",") + gene_name_str = ",".join(gene_name_str_list) query = """ SELECT -- cgit v1.2.3