mirror of
https://github.com/fjosw/pyerrors.git
synced 2025-05-14 19:43:41 +02:00
Impr/fix refactor sfcf read (#164)
* refactor read_sfcf * adding tests for find_corr and read_compact_file * add necessary broken data for tests * fixed appended mode reading * factored out sort_names and find_files * now also using sort_files in sfcf.py * edited tests to fit with new structure * added find_files function * shifted helpfunctions to bottom of file * removed some debug lines * linting * Fixed requested changes, added silent mode * added Exception if correlator is not found by read_append_rep * use tmp_path fixture * linting silent keyword * try to fix testing for a_bb * tests: Exception testing in test_find_corr made more explicit. --------- Co-authored-by: Fabian Joswig <fabian.joswig@ed.ac.uk>
This commit is contained in:
Justus Kuhlmann
GitHub
parent
991199a680
commit
41fec09816
7 changed files with 880 additions and 315 deletions
|
|
@ -1,6 +1,5 @@
|
|||
import os
|
||||
import fnmatch
|
||||
import re
|
||||
import struct
|
||||
import warnings
|
||||
import numpy as np # Thinly-wrapped numpy
|
||||
|
|
@ -10,75 +9,7 @@ from ..obs import Obs
|
|||
from ..fits import fit_lin
|
||||
from ..obs import CObs
|
||||
from ..correlators import Corr
|
||||
|
||||
|
||||
def _find_files(path, prefix, postfix, ext, known_files=[]):
|
||||
found = []
|
||||
files = []
|
||||
|
||||
if postfix != "":
|
||||
if postfix[-1] != ".":
|
||||
postfix = postfix + "."
|
||||
if postfix[0] != ".":
|
||||
postfix = "." + postfix
|
||||
|
||||
if ext[0] == ".":
|
||||
ext = ext[1:]
|
||||
|
||||
pattern = prefix + "*" + postfix + ext
|
||||
|
||||
for (dirpath, dirnames, filenames) in os.walk(path + "/"):
|
||||
found.extend(filenames)
|
||||
break
|
||||
|
||||
if known_files != []:
|
||||
for kf in known_files:
|
||||
if kf not in found:
|
||||
raise FileNotFoundError("Given file " + kf + " does not exist!")
|
||||
|
||||
return known_files
|
||||
|
||||
if not found:
|
||||
raise FileNotFoundError(f"Error, directory '{path}' not found")
|
||||
|
||||
for f in found:
|
||||
if fnmatch.fnmatch(f, pattern):
|
||||
files.append(f)
|
||||
|
||||
if files == []:
|
||||
raise Exception("No files found after pattern filter!")
|
||||
|
||||
files = _sort_names(files)
|
||||
return files
|
||||
|
||||
|
||||
def _sort_names(ll):
|
||||
r_pattern = r'r(\d+)'
|
||||
id_pattern = r'id(\d+)'
|
||||
|
||||
# sort list by id first
|
||||
if all([re.search(id_pattern, entry) for entry in ll]):
|
||||
ll.sort(key=lambda x: int(re.findall(id_pattern, x)[0]))
|
||||
# then by replikum
|
||||
if all([re.search(r_pattern, entry) for entry in ll]):
|
||||
ll.sort(key=lambda x: int(re.findall(r_pattern, x)[0]))
|
||||
# as the rearrangements by one key let the other key untouched, the list is sorted now
|
||||
|
||||
else:
|
||||
# fallback
|
||||
sames = ''
|
||||
if len(ll) > 1:
|
||||
for i in range(len(ll[0])):
|
||||
checking = ll[0][i]
|
||||
for rn in ll[1:]:
|
||||
is_same = (rn[i] == checking)
|
||||
if is_same:
|
||||
sames += checking
|
||||
else:
|
||||
break
|
||||
print(ll[0][len(sames):])
|
||||
ll.sort(key=lambda x: int(re.findall(r'\d+', x[len(sames):])[0]))
|
||||
return ll
|
||||
from .utils import sort_names
|
||||
|
||||
|
||||
def read_rwms(path, prefix, version='2.0', names=None, **kwargs):
|
||||
|
|
@ -171,7 +102,7 @@ def read_rwms(path, prefix, version='2.0', names=None, **kwargs):
|
|||
else:
|
||||
rep_names = names
|
||||
|
||||
rep_names = _sort_names(rep_names)
|
||||
rep_names = sort_names(rep_names)
|
||||
|
||||
print_err = 0
|
||||
if 'print_err' in kwargs:
|
||||
|
|
@ -561,6 +492,46 @@ def _parse_array_openQCD2(d, n, size, wa, quadrupel=False):
|
|||
return arr
|
||||
|
||||
|
||||
def _find_files(path, prefix, postfix, ext, known_files=[]):
|
||||
found = []
|
||||
files = []
|
||||
|
||||
if postfix != "":
|
||||
if postfix[-1] != ".":
|
||||
postfix = postfix + "."
|
||||
if postfix[0] != ".":
|
||||
postfix = "." + postfix
|
||||
|
||||
if ext[0] == ".":
|
||||
ext = ext[1:]
|
||||
|
||||
pattern = prefix + "*" + postfix + ext
|
||||
|
||||
for (dirpath, dirnames, filenames) in os.walk(path + "/"):
|
||||
found.extend(filenames)
|
||||
break
|
||||
|
||||
if known_files != []:
|
||||
for kf in known_files:
|
||||
if kf not in found:
|
||||
raise FileNotFoundError("Given file " + kf + " does not exist!")
|
||||
|
||||
return known_files
|
||||
|
||||
if not found:
|
||||
raise FileNotFoundError(f"Error, directory '{path}' not found")
|
||||
|
||||
for f in found:
|
||||
if fnmatch.fnmatch(f, pattern):
|
||||
files.append(f)
|
||||
|
||||
if files == []:
|
||||
raise Exception("No files found after pattern filter!")
|
||||
|
||||
files = sort_names(files)
|
||||
return files
|
||||
|
||||
|
||||
def _read_array_openQCD2(fp):
|
||||
t = fp.read(4)
|
||||
d = struct.unpack('i', t)[0]
|
||||
|
|
@ -974,7 +945,7 @@ def _read_flow_obs(path, prefix, c, dtr_cnfg=1, version="openQCD", obspos=0, sum
|
|||
|
||||
deltas.append(Q_top)
|
||||
|
||||
rep_names = _sort_names(rep_names)
|
||||
rep_names = sort_names(rep_names)
|
||||
|
||||
idl = [range(int(configlist[rep][r_start_index[rep]]), int(configlist[rep][r_stop_index[rep]]) + 1, 1) for rep in range(len(deltas))]
|
||||
deltas = [deltas[nrep][r_start_index[nrep]:r_stop_index[nrep] + 1] for nrep in range(len(deltas))]
|
||||
|
|
|
|||
|
|
@ -3,11 +3,11 @@ import fnmatch
|
|||
import re
|
||||
import numpy as np # Thinly-wrapped numpy
|
||||
from ..obs import Obs
|
||||
from . import utils
|
||||
from .utils import sort_names, check_idl
|
||||
|
||||
|
||||
def read_sfcf(path, prefix, name, quarks='.*', corr_type='bi', noffset=0, wf=0, wf2=0, version="1.0c", cfg_separator="n", **kwargs):
|
||||
"""Read sfcf c format from given folder structure.
|
||||
def read_sfcf(path, prefix, name, quarks='.*', corr_type='bi', noffset=0, wf=0, wf2=0, version="1.0c", cfg_separator="n", silent=False, **kwargs):
|
||||
"""Read sfcf files from given folder structure.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
|
|
@ -71,8 +71,7 @@ def read_sfcf(path, prefix, name, quarks='.*', corr_type='bi', noffset=0, wf=0,
|
|||
else:
|
||||
im = 0
|
||||
part = 'real'
|
||||
if "replica" in kwargs:
|
||||
reps = kwargs.get("replica")
|
||||
|
||||
if corr_type == 'bb':
|
||||
b2b = True
|
||||
single = True
|
||||
|
|
@ -82,8 +81,7 @@ def read_sfcf(path, prefix, name, quarks='.*', corr_type='bi', noffset=0, wf=0,
|
|||
else:
|
||||
b2b = False
|
||||
single = False
|
||||
compact = True
|
||||
appended = False
|
||||
|
||||
known_versions = ["0.0", "1.0", "2.0", "1.0c", "2.0c", "1.0a", "2.0a"]
|
||||
|
||||
if version not in known_versions:
|
||||
|
|
@ -99,12 +97,9 @@ def read_sfcf(path, prefix, name, quarks='.*', corr_type='bi', noffset=0, wf=0,
|
|||
else:
|
||||
compact = False
|
||||
appended = False
|
||||
read = 0
|
||||
T = 0
|
||||
start = 0
|
||||
ls = []
|
||||
if "replica" in kwargs:
|
||||
ls = reps
|
||||
ls = kwargs.get("replica")
|
||||
else:
|
||||
for (dirpath, dirnames, filenames) in os.walk(path):
|
||||
if not appended:
|
||||
|
|
@ -120,74 +115,38 @@ def read_sfcf(path, prefix, name, quarks='.*', corr_type='bi', noffset=0, wf=0,
|
|||
ls = list(set(ls) - set([exc]))
|
||||
|
||||
if not appended:
|
||||
if len(ls) > 1:
|
||||
# New version, to cope with ids, etc.
|
||||
ls.sort(key=lambda x: int(re.findall(r'\d+', x[len(prefix):])[0]))
|
||||
ls = sort_names(ls)
|
||||
replica = len(ls)
|
||||
|
||||
else:
|
||||
replica = len([file.split(".")[-1] for file in ls]) // len(set([file.split(".")[-1] for file in ls]))
|
||||
print('Read', part, 'part of', name, 'from', prefix[:-1],
|
||||
',', replica, 'replica')
|
||||
if not silent:
|
||||
print('Read', part, 'part of', name, 'from', prefix[:-1], ',', replica, 'replica')
|
||||
|
||||
if 'names' in kwargs:
|
||||
new_names = kwargs.get('names')
|
||||
if len(new_names) != len(set(new_names)):
|
||||
raise Exception("names are not unique!")
|
||||
if len(new_names) != replica:
|
||||
raise Exception('Names does not have the required length', replica)
|
||||
raise Exception('names should have the length', replica)
|
||||
|
||||
else:
|
||||
new_names = []
|
||||
ens_name = kwargs.get("ens_name")
|
||||
if not appended:
|
||||
for entry in ls:
|
||||
try:
|
||||
idx = entry.index('r')
|
||||
except Exception:
|
||||
raise Exception("Automatic recognition of replicum failed, please enter the key word 'names'.")
|
||||
|
||||
if 'ens_name' in kwargs:
|
||||
new_names.append(kwargs.get('ens_name') + '|' + entry[idx:])
|
||||
else:
|
||||
new_names.append(entry[:idx] + '|' + entry[idx:])
|
||||
new_names = _get_rep_names(ls, ens_name)
|
||||
else:
|
||||
new_names = _get_appended_rep_names(ls, prefix, name, ens_name)
|
||||
new_names = sort_names(new_names)
|
||||
|
||||
for exc in ls:
|
||||
if not fnmatch.fnmatch(exc, prefix + '*.' + name):
|
||||
ls = list(set(ls) - set([exc]))
|
||||
ls.sort(key=lambda x: int(re.findall(r'\d+', x)[-1]))
|
||||
for entry in ls:
|
||||
myentry = entry[:-len(name) - 1]
|
||||
try:
|
||||
idx = myentry.index('r')
|
||||
except Exception:
|
||||
raise Exception("Automatic recognition of replicum failed, please enter the key word 'names'.")
|
||||
|
||||
if 'ens_name' in kwargs:
|
||||
new_names.append(kwargs.get('ens_name') + '|' + myentry[idx:])
|
||||
else:
|
||||
new_names.append(myentry[:idx] + '|' + myentry[idx:])
|
||||
idl = []
|
||||
if not appended:
|
||||
for i, item in enumerate(ls):
|
||||
sub_ls = []
|
||||
rep_path = path + '/' + item
|
||||
if "files" in kwargs:
|
||||
sub_ls = kwargs.get("files")
|
||||
sub_ls.sort(key=lambda x: int(re.findall(r'\d+', x)[-1]))
|
||||
files = kwargs.get("files")
|
||||
else:
|
||||
for (dirpath, dirnames, filenames) in os.walk(path + '/' + item):
|
||||
if compact:
|
||||
sub_ls.extend(filenames)
|
||||
else:
|
||||
sub_ls.extend(dirnames)
|
||||
break
|
||||
if compact:
|
||||
for exc in sub_ls:
|
||||
if not fnmatch.fnmatch(exc, prefix + '*'):
|
||||
sub_ls = list(set(sub_ls) - set([exc]))
|
||||
sub_ls.sort(key=lambda x: int(re.findall(r'\d+', x)[-1]))
|
||||
else:
|
||||
for exc in sub_ls:
|
||||
if not fnmatch.fnmatch(exc, 'cfg*'):
|
||||
sub_ls = list(set(sub_ls) - set([exc]))
|
||||
sub_ls.sort(key=lambda x: int(x[3:]))
|
||||
files = []
|
||||
sub_ls = _find_files(rep_path, prefix, compact, files)
|
||||
rep_idl = []
|
||||
no_cfg = len(sub_ls)
|
||||
for cfg in sub_ls:
|
||||
|
|
@ -200,7 +159,8 @@ def read_sfcf(path, prefix, name, quarks='.*', corr_type='bi', noffset=0, wf=0,
|
|||
raise Exception("Couldn't parse idl from directroy, problem with file " + cfg)
|
||||
rep_idl.sort()
|
||||
# maybe there is a better way to print the idls
|
||||
print(item, ':', no_cfg, ' configurations')
|
||||
if not silent:
|
||||
print(item, ':', no_cfg, ' configurations')
|
||||
idl.append(rep_idl)
|
||||
# here we have found all the files we need to look into.
|
||||
if i == 0:
|
||||
|
|
@ -209,88 +169,37 @@ def read_sfcf(path, prefix, name, quarks='.*', corr_type='bi', noffset=0, wf=0,
|
|||
# to do so, the pattern needed is put together
|
||||
# from the input values
|
||||
if version == "0.0":
|
||||
pattern = "# " + name + " : offset " + str(noffset) + ", wf " + str(wf)
|
||||
# if b2b, a second wf is needed
|
||||
if b2b:
|
||||
pattern += ", wf_2 " + str(wf2)
|
||||
qs = quarks.split(" ")
|
||||
pattern += " : " + qs[0] + " - " + qs[1]
|
||||
file = open(path + '/' + item + '/' + sub_ls[0] + '/' + name, "r")
|
||||
for k, line in enumerate(file):
|
||||
if read == 1 and not line.strip() and k > start + 1:
|
||||
break
|
||||
if read == 1 and k >= start:
|
||||
T += 1
|
||||
if pattern in line:
|
||||
read = 1
|
||||
start = k + 1
|
||||
print(str(T) + " entries found.")
|
||||
file.close()
|
||||
file = path + '/' + item + '/' + sub_ls[0] + '/' + name
|
||||
else:
|
||||
pattern = 'name ' + name + '\nquarks ' + quarks + '\noffset ' + str(noffset) + '\nwf ' + str(wf)
|
||||
if b2b:
|
||||
pattern += '\nwf_2 ' + str(wf2)
|
||||
# and the file is parsed through to find the pattern
|
||||
if compact:
|
||||
file = open(path + '/' + item + '/' + sub_ls[0], "r")
|
||||
file = path + '/' + item + '/' + sub_ls[0]
|
||||
else:
|
||||
# for non-compactified versions of the files
|
||||
file = open(path + '/' + item + '/' + sub_ls[0] + '/' + name, "r")
|
||||
file = path + '/' + item + '/' + sub_ls[0] + '/' + name
|
||||
|
||||
content = file.read()
|
||||
match = re.search(pattern, content)
|
||||
if match:
|
||||
start_read = content.count('\n', 0, match.start()) + 5 + b2b
|
||||
end_match = re.search(r'\n\s*\n', content[match.start():])
|
||||
T = content[match.start():].count('\n', 0, end_match.start()) - 4 - b2b
|
||||
assert T > 0
|
||||
print(T, 'entries, starting to read in line', start_read)
|
||||
file.close()
|
||||
else:
|
||||
file.close()
|
||||
raise Exception('Correlator with pattern\n' + pattern + '\nnot found.')
|
||||
pattern = _make_pattern(version, name, noffset, wf, wf2, b2b, quarks)
|
||||
start_read, T = _find_correlator(file, version, pattern, b2b, silent=silent)
|
||||
|
||||
# we found where the correlator
|
||||
# that is to be read is in the files
|
||||
# after preparing the datastructure
|
||||
# preparing the datastructure
|
||||
# the correlators get parsed into...
|
||||
deltas = []
|
||||
for j in range(T):
|
||||
deltas.append([])
|
||||
|
||||
for t in range(T):
|
||||
deltas[t].append(np.zeros(no_cfg))
|
||||
if compact:
|
||||
for cfg in range(no_cfg):
|
||||
with open(path + '/' + item + '/' + sub_ls[cfg]) as fp:
|
||||
lines = fp.readlines()
|
||||
# check, if the correlator is in fact
|
||||
# printed completely
|
||||
if (start_read + T > len(lines)):
|
||||
raise Exception("EOF before end of correlator data! Maybe " + path + '/' + item + '/' + sub_ls[cfg] + " is corrupted?")
|
||||
# and start to read the correlator.
|
||||
# the range here is chosen like this,
|
||||
# since this allows for implementing
|
||||
# a security check for every read correlator later...
|
||||
for k in range(start_read - 6, start_read + T):
|
||||
if k == start_read - 5 - b2b:
|
||||
if lines[k].strip() != 'name ' + name:
|
||||
raise Exception('Wrong format', sub_ls[cfg])
|
||||
if (k >= start_read and k < start_read + T):
|
||||
floats = list(map(float, lines[k].split()))
|
||||
deltas[k - start_read][i][cfg] = floats[-2:][im]
|
||||
rep_deltas = _read_compact_rep(path, item, sub_ls, start_read, T, b2b, name, im)
|
||||
|
||||
for t in range(T):
|
||||
deltas[t].append(rep_deltas[t])
|
||||
else:
|
||||
for t in range(T):
|
||||
deltas[t].append(np.zeros(no_cfg))
|
||||
for cnfg, subitem in enumerate(sub_ls):
|
||||
with open(path + '/' + item + '/' + subitem + '/' + name) as fp:
|
||||
# since the non-compatified files
|
||||
# are typically not so long,
|
||||
# we can iterate over the whole file.
|
||||
# here one can also implement the chekc from above.
|
||||
for k, line in enumerate(fp):
|
||||
if (k >= start_read and k < start_read + T):
|
||||
floats = list(map(float, line.split()))
|
||||
if version == "0.0":
|
||||
deltas[k - start][i][cnfg] = floats[im - single]
|
||||
deltas[k - start_read][i][cnfg] = floats[im - single]
|
||||
else:
|
||||
deltas[k - start_read][i][cnfg] = floats[1 + im - single]
|
||||
|
||||
|
|
@ -301,71 +210,237 @@ def read_sfcf(path, prefix, name, quarks='.*', corr_type='bi', noffset=0, wf=0,
|
|||
for exc in ls:
|
||||
if not fnmatch.fnmatch(exc, prefix + '*.' + name):
|
||||
ls = list(set(ls) - set([exc]))
|
||||
ls.sort(key=lambda x: int(re.findall(r'\d+', x)[-1]))
|
||||
pattern = 'name ' + name + '\nquarks ' + quarks + '\noffset ' + str(noffset) + '\nwf ' + str(wf)
|
||||
if b2b:
|
||||
pattern += '\nwf_2 ' + str(wf2)
|
||||
ls.sort(key=lambda x: int(re.findall(r'\d+', x)[-1]))
|
||||
pattern = _make_pattern(version, name, noffset, wf, wf2, b2b, quarks)
|
||||
deltas = []
|
||||
for rep, file in enumerate(ls):
|
||||
rep_idl = []
|
||||
with open(path + '/' + file, 'r') as fp:
|
||||
content = fp.readlines()
|
||||
data_starts = []
|
||||
for linenumber, line in enumerate(content):
|
||||
if "[run]" in line:
|
||||
data_starts.append(linenumber)
|
||||
if len(set([data_starts[i] - data_starts[i - 1] for i in range(1, len(data_starts))])) > 1:
|
||||
raise Exception("Irregularities in file structure found, not all runs have the same output length")
|
||||
chunk = content[:data_starts[1]]
|
||||
for linenumber, line in enumerate(chunk):
|
||||
if line.startswith("gauge_name"):
|
||||
gauge_line = linenumber
|
||||
elif line.startswith("[correlator]"):
|
||||
corr_line = linenumber
|
||||
found_pat = ""
|
||||
for li in chunk[corr_line + 1: corr_line + 6 + b2b]:
|
||||
found_pat += li
|
||||
if re.search(pattern, found_pat):
|
||||
start_read = corr_line + 7 + b2b
|
||||
break
|
||||
endline = corr_line + 6 + b2b
|
||||
while not chunk[endline] == "\n":
|
||||
endline += 1
|
||||
T = endline - start_read
|
||||
if rep == 0:
|
||||
deltas = []
|
||||
for t in range(T):
|
||||
deltas.append([])
|
||||
filename = path + '/' + file
|
||||
T, rep_idl, rep_data = _read_append_rep(filename, pattern, b2b, cfg_separator, im, single)
|
||||
if rep == 0:
|
||||
for t in range(T):
|
||||
deltas[t].append(np.zeros(len(data_starts)))
|
||||
# all other chunks should follow the same structure
|
||||
for cnfg in range(len(data_starts)):
|
||||
start = data_starts[cnfg]
|
||||
stop = start + data_starts[1]
|
||||
chunk = content[start:stop]
|
||||
try:
|
||||
rep_idl.append(int(chunk[gauge_line].split(cfg_separator)[-1]))
|
||||
except Exception:
|
||||
raise Exception("Couldn't parse idl from directory, problem with chunk around line ", gauge_line)
|
||||
|
||||
found_pat = ""
|
||||
for li in chunk[corr_line + 1:corr_line + 6 + b2b]:
|
||||
found_pat += li
|
||||
if re.search(pattern, found_pat):
|
||||
for t, line in enumerate(chunk[start_read:start_read + T]):
|
||||
floats = list(map(float, line.split()))
|
||||
deltas[t][rep][cnfg] = floats[im + 1 - single]
|
||||
deltas.append([])
|
||||
for t in range(T):
|
||||
deltas[t].append(rep_data[t])
|
||||
idl.append(rep_idl)
|
||||
|
||||
if "check_configs" in kwargs:
|
||||
print("Checking for missing configs...")
|
||||
if not silent:
|
||||
print("Checking for missing configs...")
|
||||
che = kwargs.get("check_configs")
|
||||
if not (len(che) == len(idl)):
|
||||
raise Exception("check_configs has to be the same length as replica!")
|
||||
for r in range(len(idl)):
|
||||
print("checking " + new_names[r])
|
||||
utils.check_idl(idl[r], che[r])
|
||||
print("Done")
|
||||
if not silent:
|
||||
print("checking " + new_names[r])
|
||||
check_idl(idl[r], che[r])
|
||||
if not silent:
|
||||
print("Done")
|
||||
result = []
|
||||
for t in range(T):
|
||||
result.append(Obs(deltas[t], new_names, idl=idl))
|
||||
return result
|
||||
|
||||
|
||||
def _find_files(rep_path, prefix, compact, files=[]):
|
||||
sub_ls = []
|
||||
if not files == []:
|
||||
files.sort(key=lambda x: int(re.findall(r'\d+', x)[-1]))
|
||||
else:
|
||||
for (dirpath, dirnames, filenames) in os.walk(rep_path):
|
||||
if compact:
|
||||
sub_ls.extend(filenames)
|
||||
else:
|
||||
sub_ls.extend(dirnames)
|
||||
break
|
||||
if compact:
|
||||
for exc in sub_ls:
|
||||
if not fnmatch.fnmatch(exc, prefix + '*'):
|
||||
sub_ls = list(set(sub_ls) - set([exc]))
|
||||
sub_ls.sort(key=lambda x: int(re.findall(r'\d+', x)[-1]))
|
||||
else:
|
||||
for exc in sub_ls:
|
||||
if not fnmatch.fnmatch(exc, 'cfg*'):
|
||||
sub_ls = list(set(sub_ls) - set([exc]))
|
||||
sub_ls.sort(key=lambda x: int(x[3:]))
|
||||
files = sub_ls
|
||||
if len(files) == 0:
|
||||
raise FileNotFoundError("Did not find files in", rep_path, "with prefix", prefix, "and the given structure.")
|
||||
return files
|
||||
|
||||
|
||||
def _make_pattern(version, name, noffset, wf, wf2, b2b, quarks):
|
||||
if version == "0.0":
|
||||
pattern = "# " + name + " : offset " + str(noffset) + ", wf " + str(wf)
|
||||
if b2b:
|
||||
pattern += ", wf_2 " + str(wf2)
|
||||
qs = quarks.split(" ")
|
||||
pattern += " : " + qs[0] + " - " + qs[1]
|
||||
else:
|
||||
pattern = 'name ' + name + '\nquarks ' + quarks + '\noffset ' + str(noffset) + '\nwf ' + str(wf)
|
||||
if b2b:
|
||||
pattern += '\nwf_2 ' + str(wf2)
|
||||
return pattern
|
||||
|
||||
|
||||
def _find_correlator(file_name, version, pattern, b2b, silent=False):
|
||||
T = 0
|
||||
|
||||
file = open(file_name, "r")
|
||||
|
||||
content = file.read()
|
||||
match = re.search(pattern, content)
|
||||
if match:
|
||||
if version == "0.0":
|
||||
start_read = content.count('\n', 0, match.start()) + 1
|
||||
T = content.count('\n', start_read)
|
||||
else:
|
||||
start_read = content.count('\n', 0, match.start()) + 5 + b2b
|
||||
end_match = re.search(r'\n\s*\n', content[match.start():])
|
||||
T = content[match.start():].count('\n', 0, end_match.start()) - 4 - b2b
|
||||
if not T > 0:
|
||||
raise ValueError("Correlator with pattern\n" + pattern + "\nis empty!")
|
||||
if not silent:
|
||||
print(T, 'entries, starting to read in line', start_read)
|
||||
|
||||
else:
|
||||
file.close()
|
||||
raise ValueError('Correlator with pattern\n' + pattern + '\nnot found.')
|
||||
|
||||
file.close()
|
||||
return start_read, T
|
||||
|
||||
|
||||
def _read_compact_file(rep_path, config_file, start_read, T, b2b, name, im):
|
||||
with open(rep_path + config_file) as fp:
|
||||
lines = fp.readlines()
|
||||
# check, if the correlator is in fact
|
||||
# printed completely
|
||||
if (start_read + T + 1 > len(lines)):
|
||||
raise Exception("EOF before end of correlator data! Maybe " + rep_path + config_file + " is corrupted?")
|
||||
corr_lines = lines[start_read - 6: start_read + T]
|
||||
del lines
|
||||
t_vals = []
|
||||
|
||||
if corr_lines[1 - b2b].strip() != 'name ' + name:
|
||||
raise Exception('Wrong format in file', config_file)
|
||||
|
||||
for k in range(6, T + 6):
|
||||
floats = list(map(float, corr_lines[k].split()))
|
||||
t_vals.append(floats[-2:][im])
|
||||
return t_vals
|
||||
|
||||
|
||||
def _read_compact_rep(path, rep, sub_ls, start_read, T, b2b, name, im):
|
||||
rep_path = path + '/' + rep + '/'
|
||||
no_cfg = len(sub_ls)
|
||||
deltas = []
|
||||
for t in range(T):
|
||||
deltas.append(np.zeros(no_cfg))
|
||||
for cfg in range(no_cfg):
|
||||
cfg_file = sub_ls[cfg]
|
||||
cfg_data = _read_compact_file(rep_path, cfg_file, start_read, T, b2b, name, im)
|
||||
for t in range(T):
|
||||
deltas[t][cfg] = cfg_data[t]
|
||||
return deltas
|
||||
|
||||
|
||||
def _read_chunk(chunk, gauge_line, cfg_sep, start_read, T, corr_line, b2b, pattern, im, single):
|
||||
try:
|
||||
idl = int(chunk[gauge_line].split(cfg_sep)[-1])
|
||||
except Exception:
|
||||
raise Exception("Couldn't parse idl from directory, problem with chunk around line ", gauge_line)
|
||||
|
||||
found_pat = ""
|
||||
data = []
|
||||
for li in chunk[corr_line + 1:corr_line + 6 + b2b]:
|
||||
found_pat += li
|
||||
if re.search(pattern, found_pat):
|
||||
for t, line in enumerate(chunk[start_read:start_read + T]):
|
||||
floats = list(map(float, line.split()))
|
||||
data.append(floats[im + 1 - single])
|
||||
return idl, data
|
||||
|
||||
|
||||
def _read_append_rep(filename, pattern, b2b, cfg_separator, im, single):
|
||||
with open(filename, 'r') as fp:
|
||||
content = fp.readlines()
|
||||
data_starts = []
|
||||
for linenumber, line in enumerate(content):
|
||||
if "[run]" in line:
|
||||
data_starts.append(linenumber)
|
||||
if len(set([data_starts[i] - data_starts[i - 1] for i in range(1, len(data_starts))])) > 1:
|
||||
raise Exception("Irregularities in file structure found, not all runs have the same output length")
|
||||
chunk = content[:data_starts[1]]
|
||||
for linenumber, line in enumerate(chunk):
|
||||
if line.startswith("gauge_name"):
|
||||
gauge_line = linenumber
|
||||
elif line.startswith("[correlator]"):
|
||||
corr_line = linenumber
|
||||
found_pat = ""
|
||||
for li in chunk[corr_line + 1: corr_line + 6 + b2b]:
|
||||
found_pat += li
|
||||
if re.search(pattern, found_pat):
|
||||
start_read = corr_line + 7 + b2b
|
||||
break
|
||||
else:
|
||||
raise ValueError("Did not find pattern\n", pattern, "\nin\n", filename)
|
||||
endline = corr_line + 6 + b2b
|
||||
while not chunk[endline] == "\n":
|
||||
endline += 1
|
||||
T = endline - start_read
|
||||
|
||||
# all other chunks should follow the same structure
|
||||
rep_idl = []
|
||||
rep_data = []
|
||||
|
||||
for cnfg in range(len(data_starts)):
|
||||
start = data_starts[cnfg]
|
||||
stop = start + data_starts[1]
|
||||
chunk = content[start:stop]
|
||||
idl, data = _read_chunk(chunk, gauge_line, cfg_separator, start_read, T, corr_line, b2b, pattern, im, single)
|
||||
rep_idl.append(idl)
|
||||
rep_data.append(data)
|
||||
|
||||
data = []
|
||||
|
||||
for t in range(T):
|
||||
data.append([])
|
||||
for c in range(len(rep_data)):
|
||||
data[t].append(rep_data[c][t])
|
||||
return T, rep_idl, data
|
||||
|
||||
|
||||
def _get_rep_names(ls, ens_name=None):
|
||||
new_names = []
|
||||
for entry in ls:
|
||||
try:
|
||||
idx = entry.index('r')
|
||||
except Exception:
|
||||
raise Exception("Automatic recognition of replicum failed, please enter the key word 'names'.")
|
||||
|
||||
if ens_name:
|
||||
new_names.append('ens_name' + '|' + entry[idx:])
|
||||
else:
|
||||
new_names.append(entry[:idx] + '|' + entry[idx:])
|
||||
return new_names
|
||||
|
||||
|
||||
def _get_appended_rep_names(ls, prefix, name, ens_name=None):
|
||||
new_names = []
|
||||
for exc in ls:
|
||||
if not fnmatch.fnmatch(exc, prefix + '*.' + name):
|
||||
ls = list(set(ls) - set([exc]))
|
||||
ls.sort(key=lambda x: int(re.findall(r'\d+', x)[-1]))
|
||||
for entry in ls:
|
||||
myentry = entry[:-len(name) - 1]
|
||||
try:
|
||||
idx = myentry.index('r')
|
||||
except Exception:
|
||||
raise Exception("Automatic recognition of replicum failed, please enter the key word 'names'.")
|
||||
|
||||
if ens_name:
|
||||
new_names.append('ens_name' + '|' + entry[idx:])
|
||||
else:
|
||||
new_names.append(myentry[:idx] + '|' + myentry[idx:])
|
||||
return new_names
|
||||
|
|
|
|||
|
|
@ -1,6 +1,51 @@
|
|||
import re
|
||||
"""Utilities for the input"""
|
||||
|
||||
|
||||
def sort_names(ll):
|
||||
"""Sorts a list of names of replika with searches for `r` and `id` in the replikum string.
|
||||
If this search fails, a fallback method is used,
|
||||
where the strings are simply compared and the first diffeing numeral is used for differentiation.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
ll: list
|
||||
list to sort
|
||||
|
||||
Returns
|
||||
-------
|
||||
ll: list
|
||||
sorted list
|
||||
"""
|
||||
if len(ll) > 1:
|
||||
r_pattern = r'r(\d+)'
|
||||
id_pattern = r'id(\d+)'
|
||||
|
||||
# sort list by id first
|
||||
if all([re.search(id_pattern, entry) for entry in ll]):
|
||||
ll.sort(key=lambda x: int(re.findall(id_pattern, x)[0]))
|
||||
# then by replikum
|
||||
if all([re.search(r_pattern, entry) for entry in ll]):
|
||||
ll.sort(key=lambda x: int(re.findall(r_pattern, x)[0]))
|
||||
# as the rearrangements by one key let the other key untouched, the list is sorted now
|
||||
|
||||
else:
|
||||
# fallback
|
||||
sames = ''
|
||||
if len(ll) > 1:
|
||||
for i in range(len(ll[0])):
|
||||
checking = ll[0][i]
|
||||
for rn in ll[1:]:
|
||||
is_same = (rn[i] == checking)
|
||||
if is_same:
|
||||
sames += checking
|
||||
else:
|
||||
break
|
||||
print("Using prefix:", ll[0][len(sames):])
|
||||
ll.sort(key=lambda x: int(re.findall(r'\d+', x[len(sames):])[0]))
|
||||
return ll
|
||||
|
||||
|
||||
def check_idl(idl, che):
|
||||
"""Checks if list of configurations is contained in an idl
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue