Make regex patterns raw strings

boost_adaptbx/boost/python.py

@@ -165,7 +165,7 @@ class gcc_version(object):
 
  def __init__(self):
  pat = r" \s* = \s* (\d+) \s+"
- m = re.search("__GNUC__ %s __GNUC_MINOR__ %s __GNUC_PATCHLEVEL__ %s"
+ m = re.search(r"__GNUC__ %s __GNUC_MINOR__ %s __GNUC_PATCHLEVEL__ %s"
  % ((pat,)*3),
  platform_info, re.X|re.M|re.S)
  if not m:

cctbx/eltbx/attenuation_coefficient.py

@@ -80,16 +80,16 @@ def chemlex(formula):
  import re
 
  # Check that the formula is valid
- if re.match('^([A-Z][a-z]{0,2}[1-9]?)*$', formula):
+ if re.match(r'^([A-Z][a-z]{0,2}[1-9]?)*$', formula):
 
  # Split the components by capital letter
- comp = re.findall('[A-Z][^A-Z]*', formula)
+ comp = re.findall(r'[A-Z][^A-Z]*', formula)
 
  # For each component split into element and number
  el_num = []
  for c in comp:
 
- r = re.compile('([A-Z][a-z]{0,2})([1-9]+)')
+ r = re.compile(r'([A-Z][a-z]{0,2})([1-9]+)')
  m = r.match(c)
  if m:
  el = m.group(1)

dox.sphinx/conf.py

@@ -81,7 +81,7 @@ def boostFuncSignature(name,obj,removeSelf=False):
  if len(docc)<2: return None,docc
  doc1=docc[1]
  # functions with weird docstring, likely not documented by boost
- if not re.match('^'+nname+r'(.*)->.*$',doc1):
+ if not re.match(r'^'+nname+r'(.*)->.*$',doc1):
  return None,docc
  if doc1.endswith(':'): doc1=doc1[:-1]
  strippedDoc=doc.split('\n')[2:]

gltbx/util.py

@@ -45,7 +45,7 @@ def show_versions():
 def check_glx_availability():
  glxerr = easy_run.fully_buffered("glxinfo -b").stderr_lines
  for line in glxerr :
- if re.search('extension "GLX" missing', line):
+ if re.search(r'extension "GLX" missing', line):
  return False
  return True
 
@@ -58,7 +58,7 @@ def __init__(self):
  import re
  self.__dict__ = self._shared_state
  if not self._shared_state:
- vers_pat = re.compile("^((\d+)\.(\d+))(?:\.(\d+))?(?: (.*))?$")
+ vers_pat = re.compile(r"^((\d+)\.(\d+))(?:\.(\d+))?(?: (.*))?$")
  m = vers_pat.search(gl.glGetString(gl.GL_VERSION))
  self.__dict__.update(dict(zip(
  ["principal", "major_number", "minor_number", "release_number",

iotbx/bioinformatics/__init__.py

@@ -15,7 +15,7 @@
 # Wrap lines that are longer than 'width'
 def wrap(text, width):
 
- return re.findall( "[^\n]{1,%d}" % width, text )
+ return re.findall( r"[^\n]{1,%d}" % width, text )
 
 
 # Sequence headers

iotbx/cif/builders.py

@@ -770,7 +770,7 @@ def get_HL_labels(self, keys):
  or like 'HLanomA', 'HLanomB', 'HLanomC', 'HLanomD'
  Use a regular expression to group them accordingly
  """
- allmatches = re.findall("(\S*(HL(\S*)[abcdABCD](\S*)))", alllabels )
+ allmatches = re.findall(r"(\S*(HL(\S*)[abcdABCD](\S*)))", alllabels )
  HLtagslst = list(set([ (e[2], e[3]) for e in allmatches ]))
  usedkeys = []
  for m in HLtagslst:
@@ -794,7 +794,7 @@ def get_mapcoefficient_labels(self, keys):
  remainingkeys = lstkeys[:] # deep copy the list
  alllabels = " ".join(lstkeys) # _refln.FC _refln.PHIC _refln.FC_ALL _refln.PHIC_ALL _refln.FWT _refln.PHWT _refln.DELFWT _refln.PHDELWT
  mapcoefflabels = []
- PHmatches = re.findall("((\S*PH)([^I]\S*))", alllabels ) # [('_refln.PHWT', '_refln.PH', 'WT'), ('_refln.PHDELWT', '_refln.PH', 'DELWT')]
+ PHmatches = re.findall(r"((\S*PH)([^I]\S*))", alllabels ) # [('_refln.PHWT', '_refln.PH', 'WT'), ('_refln.PHDELWT', '_refln.PH', 'DELWT')]
  for label in lstkeys:
  for m in PHmatches:
  Flabel = m[1].replace("PH","F") + m[2]
@@ -803,7 +803,7 @@ def get_mapcoefficient_labels(self, keys):
  remainingkeys.remove(label)
  remainingkeys.remove(m[0])
  alllabels = " ".join(remainingkeys)
- PHImatches = re.findall("((\S*PHI)(\S*))", alllabels ) # [('_refln.PHIC', '_refln.PHI', 'C'), ('_refln.PHIC_ALL', '_refln.PHI', 'C_ALL')]
+ PHImatches = re.findall(r"((\S*PHI)(\S*))", alllabels ) # [('_refln.PHIC', '_refln.PHI', 'C'), ('_refln.PHIC_ALL', '_refln.PHI', 'C_ALL')]
  for label in lstkeys:
  for m in PHImatches:
  Flabel = m[1].replace("PHI","F") + m[2]
@@ -812,7 +812,7 @@ def get_mapcoefficient_labels(self, keys):
  remainingkeys.remove(label)
  remainingkeys.remove(m[0])
  alllabels = " ".join(remainingkeys)
- PHDELmatches = re.findall("(((\S*)PH)([^I]\S*(WT)))", alllabels ) # [('_refln.PHDELWT', '_refln.PH', '_refln.', 'DELWT', 'WT')]
+ PHDELmatches = re.findall(r"(((\S*)PH)([^I]\S*(WT)))", alllabels ) # [('_refln.PHDELWT', '_refln.PH', '_refln.', 'DELWT', 'WT')]
  for label in lstkeys:
  for m in PHDELmatches:
  Flabel = m[2] + m[3].replace("WT","FWT")
@@ -821,7 +821,7 @@ def get_mapcoefficient_labels(self, keys):
  remainingkeys.remove(label)
  remainingkeys.remove(m[0])
  alllabels = " ".join(remainingkeys)
- phase_matches = re.findall("((\S*\.)phase(_\S*))", alllabels ) # [('_refln.phase_calc', '_refln.', '')]
+ phase_matches = re.findall(r"((\S*\.)phase(_\S*))", alllabels ) # [('_refln.phase_calc', '_refln.', '')]
  for label in lstkeys:
  for m in phase_matches:
  phaselabel = m[0]
@@ -843,7 +843,7 @@ def guess_observationtype(labl):
  if labl.startswith(okey):
  return self.observation_types[okey]
  return None
- sigma_matches = re.findall("((\S*\.)SIG(\S*))", alllabels ) # catch label pairs like F(+),SIGF(+)
+ sigma_matches = re.findall(r"((\S*\.)SIG(\S*))", alllabels ) # catch label pairs like F(+),SIGF(+)
  for label in lstkeys:
  for m in sigma_matches:
  FIlabel = m[1] + m[2]
@@ -852,7 +852,7 @@ def guess_observationtype(labl):
  remainingkeys.remove(label)
  remainingkeys.remove(m[0])
  alllabels = " ".join(remainingkeys)
- sigma_matches = re.findall("((\S*)_sigma(_*\S*))", alllabels ) # [('_refln.F_meas_sigma_au', '_refln.F_meas', '_au'), ('_refln.intensity_sigma', '_refln.intensity', ''), ('_refln.pdbx_I_plus_sigma', '_refln.pdbx_I_plus', '')]
+ sigma_matches = re.findall(r"((\S*)_sigma(_*\S*))", alllabels ) # [('_refln.F_meas_sigma_au', '_refln.F_meas', '_au'), ('_refln.intensity_sigma', '_refln.intensity', ''), ('_refln.pdbx_I_plus_sigma', '_refln.pdbx_I_plus', '')]
  for label in lstkeys:
  for m in sigma_matches:
  FIlabel = m[1] + m[2]
@@ -862,8 +862,8 @@ def guess_observationtype(labl):
  remainingkeys.remove(m[0])
  alllabels = " ".join(remainingkeys)
  # catch generic meas and sigma labels, https://www.iucr.org/__data/iucr/cifdic_html/2/cif_mm.dic/index.html
- anymeas_matches = re.findall("((\S*)_meas(\S*))", alllabels ) + re.findall("((\S*)_calc(\S*))", alllabels )
- anysigma_matches = re.findall("((\S*)_sigma(\S*))", alllabels )
+ anymeas_matches = re.findall(r"((\S*)_meas(\S*))", alllabels ) + re.findall(r"((\S*)_calc(\S*))", alllabels )
+ anysigma_matches = re.findall(r"((\S*)_sigma(\S*))", alllabels )
  for mmatch in anymeas_matches:
  for smatch in anysigma_matches:
  if mmatch[1]==smatch[1] and mmatch[2]==smatch[2]:

iotbx/command_line/file_reader.py

@@ -24,7 +24,7 @@
  .caption = Any_format %s
 }
 """ % (" ".join(file_reader.standard_file_types),
- " ".join([ re.sub(" ", "_", file_reader.standard_file_descriptions[ft])
+ " ".join([ re.sub(r" ", "_", file_reader.standard_file_descriptions[ft])
  for ft in file_reader.standard_file_types ])))
 
 def run(args=(), params=None, out=sys.stdout):

iotbx/command_line/pdb_as_fasta.py

@@ -34,7 +34,7 @@ def run(args=(), params=None, out=sys.stdout):
  else :
  seq = "".join(chain.as_sequence())
  if (params.ignore_missing_residues_at_start):
- seq = re.sub("^X*", "", seq)
+ seq = re.sub(r"^X*", "", seq)
  seq_lines = []
  k = 0
  while (k < len(seq)):

iotbx/data_manager/__init__.py

@@ -39,7 +39,7 @@
 # datatypes have corresponding modules in iotbx/data_manager
 # e.g. iotbx/data_manager/model.py
 supported_datatypes = os.listdir(os.path.dirname(__file__))
-re_search = re.compile('.py$')
+re_search = re.compile(r'\.py$')
 supported_datatypes = list(filter(re_search.search, supported_datatypes))
 supported_datatypes.remove('__init__.py')
 supported_datatypes.sort()

iotbx/data_plots.py

@@ -188,11 +188,11 @@ def import_loggraph(self, lines):
  assert remainder == '', 'loggraph table has %d bytes following the table end' % len(remainder)
 
  if '$TABLE' in header:
- title = re.search('\\$TABLE\\s*:(.*?)(:|\n|$)', header, re.MULTILINE)
+ title = re.search(r'\$TABLE\s*:(.*?)(:|\n|$)', header, re.MULTILINE)
  if title:
  self.title = title.group(1).strip()
 
- graphs = re.search('\\$(GRAPHS|SCATTER)[\\s\n]*((:[^:\n]*:[^:\n]*:[^:\n]*(:|$)[\\s\n]*)*)($|\\$)', header, re.MULTILINE)
+ graphs = re.search(r'\$(GRAPHS|SCATTER)[\s\n]*((:[^:\n]*:[^:\n]*:[^:\n]*(:|$)[\s\n]*)*)($|\$)', header, re.MULTILINE)
  if graphs:
  if graphs.group(1) == 'GRAPHS':
  self.plot_type = "GRAPH"
@@ -201,7 +201,7 @@ def import_loggraph(self, lines):
  else:
  raise TypeError('Unknown graph type %s' % graphs.group(1))
  graphs = graphs.group(2)
- for graph in re.finditer(':([^:\n]*):([^:\n]*):([^:\n]*)(:|$)', graphs, re.MULTILINE):
+ for graph in re.finditer(r':([^:\n]*):([^:\n]*):([^:\n]*)(:|$)', graphs, re.MULTILINE):
  self.add_graph(name=graph.group(1),
  type=graph.group(2),
  columns=[ int(col)-1 for col in graph.group(3).split(',') ])

iotbx/detectors/__init__.py

@@ -165,5 +165,5 @@ def __str__(self):
  def get_frame_path(self, frame):
  assert isinstance(frame, int) and (frame > 0)
  serial_format = "%%0%dd" % (self.base_name.count("#"))
- format_str = re.sub("[#]{1,}", serial_format, self.base_name)
+ format_str = re.sub(r"[#]{1,}", serial_format, self.base_name)
  return format_str % frame

iotbx/file_reader.py

@@ -416,7 +416,7 @@ def _try_as_seq(self):
 # assert len(self._file_object) != 0
 # for _line in self._file_object.splitlines():
 # assert not _line.startswith(" ")
-# line = re.sub(" ", "", _line)
+# line = re.sub(r" ", "", _line)
 # assert ((len(line) == 0) or
 # (line[0] == ">") or
 # (line == "*") or

iotbx/fullprof/write_pcr.py

@@ -190,27 +190,27 @@ def __replace_match(string, match, var):
  for param in freeparams:
  if param == "scale":
  # free all scale factors
- for m in re.finditer('##_scf_##', ret):
+ for m in re.finditer(r'##_scf_##', ret):
  ret = __replace_match(ret, m , varcount)
  varcount += 1
  elif param == "lattice":
  # free all lattice parameters
- for m in re.finditer('##_lp.*?_##', ret):
+ for m in re.finditer(r'##_lp.*?_##', ret):
  if m.group(0) not in param_to_var:
  param_to_var[m.group(0)] = varcount
  varcount += 1
  ret = __replace_match(ret, m , param_to_var[m.group(0)])
  elif param == "profile":
  # free all profile parameters
- for m in re.finditer('##_prf*?_##', ret):
+ for m in re.finditer(r'##_prf*?_##', ret):
  if m.group(0) not in param_to_var:
  param_to_var[m.group(0)] = varcount
  varcount += 1
  ret = __replace_match(ret, m , param_to_var[m.group(0)])
  else:
  raise ValueError("unknown parameter type: '{0}'".format(param))
  # fix all still unhandled flags
- for m in re.finditer('##_.*?_##', ret):
+ for m in re.finditer(r'##_.*?_##', ret):
  ret = ret[:m.start()] + "0.00".rjust(len(m.group(0))) + ret[m.end():]
  ret = ret.replace('#__npar__#', str(varcount-1))
  return ret

iotbx/logfiles.py

@@ -16,7 +16,7 @@ def float_or_none(n):
 
 def percent_to_float(value):
  assert value.endswith("%")
- return float(re.sub("\%$", "", value))
+ return float(re.sub(r"\%$", "", value))
 
 class experiment_info(object):
  def extract_all_stats(self):
@@ -471,7 +471,7 @@ def parse_xscale(lines):
  elif (fields[0] == "total"):
  overall = fields
  break
- elif re.match("^\d", line):
+ elif re.match(r"^\d", line):
  bins.append(fields)
  j += 1
  assert (len(bins) > 0) and (len(overall) == len(bins[0]))

iotbx/mtz/__init__.py

@@ -231,7 +231,7 @@ def hendrickson_lattman(self, root_label, i_coeff, anomalous_sign=None):
 class ccp4_label_decorator(label_decorator):
  def phases(self, root_label, anomalous_sign=None):
  assert (root_label in ["FWT", "DELFWT"])
- root_label = re.sub("F", "", root_label)
+ root_label = re.sub(r"F", "", root_label)
  return self.anomalous(
  "PH" + root_label + self.phases_suffix,
  anomalous_sign)

iotbx/pdb/fetch.py

@@ -34,7 +34,7 @@
 import os
 
 def looks_like_pdb_id(id):
- return (len(id) == 4) and (re.match("[1-9]{1}[a-zA-Z0-9]{3}", id))
+ return (len(id) == 4) and (re.match(r"[1-9]{1}[a-zA-Z0-9]{3}", id))
 
 def validate_pdb_id(id):
  if (not looks_like_pdb_id(id)):
@@ -77,7 +77,7 @@ def fetch(id, data_type="pdb", format="pdb", mirror="rcsb", log=None,
  cache_files = os.listdir(local_cache)
  for file_name in cache_files :
  if (len(file_name) > 4):
- file_id = re.sub("^pdb", "", file_name)[0:4]
+ file_id = re.sub(r"^pdb", "", file_name)[0:4]
  if (file_id.lower() == id):
  if (guess_file_type(file_name) == "pdb"):
  file_name = os.path.join(local_cache, file_name)

iotbx/pdb/remediation/remediator.py

@@ -334,8 +334,8 @@ def remediate(filename, remediated_out, f=None):
  pdb_file = open(filename)
 
  aa_re = re.compile(
- ' HN2 (ALA|ARG|ASN|ASP|ASX|CSE|CYS|GLN|GLU|GLX|GLY|HIS|ILE|'+
- 'LEU|LYS|MET|MSE|PHE|PRO|SER|THR|TRP|UNK|TYR|VAL)')
+ r' HN2 (ALA|ARG|ASN|ASP|ASX|CSE|CYS|GLN|GLU|GLX|GLY|HIS|ILE|'+
+ r'LEU|LYS|MET|MSE|PHE|PRO|SER|THR|TRP|UNK|TYR|VAL)')
 
  for line in pdb_file:
  line=line.rstrip()
@@ -350,7 +350,7 @@ def remediate(filename, remediated_out, f=None):
  elif re.match(r'REMARK...\D',line):
  print_line += line + "\n"
  continue
- elif re.match('REMARK 4 REMEDIATOR',line):
+ elif re.match(r'REMARK 4 REMEDIATOR',line):
  continue
  elif int(line[6:10]) > 4:
  print_line += remark4 + "\n"
@@ -390,8 +390,8 @@ def remediate(filename, remediated_out, f=None):
  m = aa_re.search(print_line)
  if m:
  res = m.group(1)
- if re.search('1H '+res,print_line) or re.search('2H '+res,print_line):
- print_line = re.sub(' HN2 '+res,'2H '+res,print_line)
+ if re.search(r'1H '+res,print_line) or re.search(r'2H '+res,print_line):
+ print_line = re.sub(r' HN2 '+res,'2H '+res,print_line)
  print_line=print_line.rstrip("\n")
 
  if not (print_line == ""):

iotbx/reflection_file_editor.py

@@ -552,9 +552,9 @@ def __init__(self, params, input_files=None, inputs_object=None,
  default_types = iotbx.mtz.default_column_types(output_array)
  if (array_types[i] is not None):
  if output_array.is_xray_amplitude_array():
- array_types[i] = re.sub("J", "F", array_types[i])
+ array_types[i] = re.sub(r"J", "F", array_types[i])
  elif output_array.is_xray_intensity_array():
- array_types[i] = re.sub("F", "J", array_types[i])
+ array_types[i] = re.sub(r"F", "J", array_types[i])
  if len(default_types) == len(array_types[i]):
  print("Recovering original column types %s" % array_types[i], file=log)
  column_types = array_types[i]
@@ -956,7 +956,7 @@ def modify_array(
  raise Sorry("Missing output labels for %s!" % array_name)
  if (array_params.column_root_label is not None):
  output_labels = None
- labels_base = re.sub(",merged$", "", array_params.labels)
+ labels_base = re.sub(r",merged$", "", array_params.labels)
  input_labels = labels_base.split(",")
  if not None in [array_params.scale_factor, array_params.scale_max] :
  raise Sorry("The parameters scale_factor and scale_max are " +

iotbx/table_one.py

@@ -271,7 +271,7 @@ def format_d_max_min(d_max_min):
  else :
  (d_max, d_min) = d_max_min
  d_max_str = "%.4g " % d_max
- d_min_str = re.sub("\.$", ".0", re.sub("0*$", "", "%.3f" % d_min))
+ d_min_str = re.sub(r"\.$", ".0", re.sub(r"0*$", "", "%.3f" % d_min))
  return "%s - %s" % (d_max_str, d_min_str)
 
 def resize_column(cell_values, alignment="right"):

libtbx/auto_build/bootstrap.py

@@ -448,9 +448,9 @@ def set_git_repository_config_to_rebase(config):
  else:
  branch = False
  remote, rebase = False, False
- if re.match('remote\s*=', line.strip()):
+ if re.match(r'remote\s*=', line.strip()):
  remote = True
- if re.match('rebase\s*=', line.strip()):
+ if re.match(r'rebase\s*=', line.strip()):
  rebase = True
  if branch and remote and not rebase:
  insertions.insert(0, (n + 1, branch))

libtbx/auto_build/create_mac_app.py

@@ -84,7 +84,7 @@ def run(args, out=sys.stdout):
 [py2app]
 argv-emulation=0""")
  f.close()
- script_name = re.sub(".pyc$", ".py", py2app.script_py2applet.__file__)
+ script_name = re.sub(r"\.pyc$", ".py", py2app.script_py2applet.__file__)
  import subprocess
  executable = sys.executable
  if (options.python_interpreter is not None):

libtbx/auto_build/setup_installer.py

@@ -230,7 +230,7 @@ def get_module(module_name):
  print("")
  print("********** FETCHING MODULES **********")
  print("")
- module_list = re.sub(",", " ", module_list)
+ module_list = re.sub(r",", " ", module_list)
  for module_name in module_list.split():
  get_module(module_name)
 
@@ -241,7 +241,7 @@ def get_module(module_name):
  base_module_dir = op.join(options.dest, installer_dir, "base")
  os.makedirs(base_module_dir)
  os.chdir(base_module_dir)
- base_module_list = re.sub(",", " ", base_module_list)
+ base_module_list = re.sub(r",", " ", base_module_list)
  for module_name in base_module_list.split():
  get_module(module_name)
 

libtbx/fastentrypoints.py

@@ -89,7 +89,7 @@ def main():
  import shutil
  import sys
  dests = sys.argv[1:] or ['.']
- filename = re.sub('\.pyc$', '.py', __file__)
+ filename = re.sub(r'\.pyc$', '.py', __file__)
 
  for dst in dests:
  shutil.copy(filename, dst)