我有一堆文件不应该受版本控制。但是，如果我不对它们进行版本控制，则构建将失败。由于这些文件包含键/值内容，因此我在其中添加了这些文件，但将实际值替换为伪值。因此，我能够通过构建，并且在VC下也没有那些实际的键/值。我将此更改提交给了VC。我还将这些文件的列表放在.gitignore文件下，如下所示：
import pandas as pd
import numpy as np
import csv
import os
import json
content = {
'rootpath' : os.path.abspath ( os.getcwd () ),
'indir' : '.',
'outdir' : 'output',
'workdir' : 'temporary',
'datafile' : 'file.csv',
'configfile' : 'configs.txt',
'savefile' : 'contents.csv',
'model' : np.arange (4),
'datafiles' : [os.path.join (os.getcwd (), 'data.csv'), os.path.join (os.getcwd (), 'data.dat')],
'data' : pd.DataFrame ( np.arange (15).reshape (3, 5) ),
'dataid' : 'g_g;r_g;r_r;',
'result' : None,
}
hmm = {
'hmm_a' : np.random.rand (9).reshape (3, 3), # test input of a two-dimensional (np.nd)array because one isn't enough and they will appear (during/after computation)
'hmm_b' : np.zeros (3),
'hmm_mu' : np.random.rand (1),
'hmm_pi' : np.random.rand (3),
'hmm_block' : np.random.rand (27).reshape (3, 3, 3), # test input of a three-dimensional (np.nd)array because of their appearance
}
'''
computation, changing pathname and filename, rest of the program
'''
write_in = content.copy ()
write_in.update (hmm)
path = os.path.join ( write_in ['rootpath'], write_in ['outdir'], write_in ['savefile'] )
p, filetype = os.path.splitext (path)
'''
if write_in == write_in ['data'] : # write_in only contains data
onlydata = True
else :
onlydata = False
'''
for c in write_in :
if type ( write_in [c] ) == np.ndarray :
write_in [c] = write_in [c].tolist ()
elif type ( write_in [c] ) == pd.DataFrame :
#write_in [c] = pd.DataFrame.to_numpy ( write_in [c], copy = True ).tolist () # needs pandas +0.24.0
write_in [c] = write_in [c].values.tolist ()
# saving as *.csv Comma Separated Values
if 'csv' in filetype or 'CSV' in filetype : # If chosen, take care when loading this file. Remember the data structure…!
if onlydata :
with open ( path, mode ) as f : # alternative 0; pd.DataFrame
write_in.to_csv ( f, header = None, index = False ) # alternative 0; pd.DataFrame
#write_in.to_csv ( path, header = None, index = False ) # alternative 1; pd.DataFrame
else : ### works.
# converting the chosen variables to linewise objects
for c in write_in :
if type ( write_in [c] ) == np.ndarray :
write_in [c] = write_in [c].tolist ()
elif type ( write_in [c] ) == pd.DataFrame :
#write_in [c] = write_in [c].to_numpy (copy = True).tolist () # alternative 2
#write_in [c] = DataFrame.to_numpy (write_in [c], copy = True).tolist () # alternative 1
write_in [c] = write_in [c].values.tolist () # alternative 0
# the saving itself
with open ( path, 'w', newline = '' ) as f :
w = csv.writer ( f, delimiter = ',', quotechar = '"' )#, quoting = csv.QUOTE_ALL ) # alternative 1; dict
for key, value in write_in.items () : # alternative 1; dict
w.writerow ( [key, value] ) # alternative 1; dict
# saving as *.json JavaScript Object Notation; the dict should be written into the file as onto the command line.
elif 'json' in filetype or 'JSON' in filetype :
if onlydata :
with open ( path, mode ) as f :
write_in.to_json (f)#, orient = 'columns' )#, orient = DataFrame )#, index = False ) # alternative 0; pd.DataFrame
else : ### works.
# converting the chosen variables to JSON serializable objects
for c in write_in :
if type ( write_in [c] ) == np.ndarray :
write_in [c] = write_in [c].tolist ()
elif type ( write_in [c] ) == pd.DataFrame :
write_in [c] = write_in [c].to_json ( orient = 'columns' )
# the saving itself
with open ( path, mode ) as f :
#f.write ( json.dumps (write_in) ) # alternative 1; dict
json.dump ( write_in, f, indent = 4 ) # alternative 0; dict
# saving as *.txt
elif 'txt' in filetype or 'TXT' in filetype :
if onlydata :
with open ( path, mode ) as f :
f.write ( str (write_in) ) ### Better make this with pd.iterrows
else :
with open ( path, mode ) as f :
f.write ( str (write_in) )
# saving as *.dat; this shouldn't make a difference for the file here as if saved as *.txt.
elif 'dat' in filetype or 'DAT' in filetype :
if onlydata :
with open ( path, mode = mode + 'b' ) as f :
f.write (write_in) ### Better make this with pd.iterrows…?
else :
with open ( path, mode = mode + 'b' ) as f :
f.write (write_in)
else :
print ( 'save_file: Unknown file format. Aborting program part.' )
现在的问题是，为了测试我的更改，我需要用实际的替换那些伪造的文件/值。但是，这样做可以在运行# from *.csv
if 'csv' in filetype or 'CSV' in filetype :
read_out = {}
with open ( path, 'r' ) as f :
reader = csv.reader (f)
for k, v in reader :
read_out [k] = v
#for line in f : # if the above fails
#(key, val) = line.split (',') # if the above fails
#read_out [key] = val # if the above fails
#d = {} # if the above fails
#for key, val in read_out.iterrows () : # if the above fails
#d [key] = val # if the above fails
# converting the str the their original dtype, determined by what's in the str; better have put it in the file…?
for a in read_out :
if read_out [a] == '' :
if 'dir' in a : # Relative paths; set *indir*, *outdir* and *workdir* to *rootpath* if not specified.
read_out [a] = '.'
elif a == 'result' : # No result was achieved.
read_out [a] = None
elif a == 'dataid' :
if '[' == read_out [a] [0] and ']' == read_out [a] [-1] and "', '" in read_out [a] :
read_out [a] = read_out [a].split ("', '") [ 1 : -1 ] # Take away the enclosing brackets -> split up the long str to multiple short ones by the separating sequence of a str (list)
elif "', '" in read_out [a] :
read_out [a] = read_out [a].split ("', '")
elif '; ' in read_out [a] :
read_out [a] = read_out [a].split ('; ')
elif ';' in read_out [a] :
read_out [a] = read_out [a].split (';')
else :
seppi = input ( "read_configs: Couldn't determine the separating character of *dataid*. Please type it (Standard: comma): " )
if seppi == '' :
seppi = ','
if seppi in read_out [a] :
read_out [a] = read_out [a].split (seppi)
else :
read_out [a] = ['g_g', 'r_g', 'r_r']
elif a == 'datafiles' : # input list of data files which weren't taken into computation yet; absolute paths
read_out [a] = read_out [a].split ("'") [ 1 : -1 : 2 ]
elif '[' == read_out [a] [0] and ']' == read_out [a] [-1] : # Should be a np.ndarray because other entries with '[' and ']' are already sorted out.
if read_out [a].count ('[') == read_out [a].count (']') == 1 : # one-dimensional array
#floats = np.array ( read_out [a] [ 1 : -1 ].split (', ') [:] ).astype (np.float128) # alternative 1
#ints = np.array ( read_out [a] [ 1 : -1 ].split (', ') [:] ).astype (np.int64) # alternative 1
floats = np.fromstring ( read_out [a] [ 1 : -1 ], dtype = np.float128, sep = ',' ) # alternative 0
ints = np.fromstring ( read_out [a] [ 1 : -1 ], dtype = np.int64, sep = ',' ) # alternative 0
if ints.all () == floats.all () and not ints.all () == np.zeros (floats.size).all () :
read_out [a] = ints
else :
read_out [a] = floats
else : # multi-dimensional array; actually works only with two-dimensional arrays.
md_array = read_out [a] [ 2 : -2 ].split ('], [') # Removing '[[' from the beginning and ']]' from the end, splitting it up to a list where the elements are the inner np.ndarrays as str.
f, i = [], []
for b in range ( len (md_array) ) : # iterating over the length of *md_array*
#floats = np.array ( md_array [b].split (', ') ).astype (np.float128) # alternative 1
#ints = np.array ( md_array [b].split (', ') ).astype (np.int64) # alternative 1
floats = np.fromstring ( md_array [b], dtype = np.float128, sep = ',' ) # alternative 0
ints = np.fromstring ( md_array [b], dtype = np.int64, sep = ',' ) # alternative 0
f.append (floats)
i.append (ints)
floats = np.array (f)
ints = np.array (i)
if ints.all () == floats.all () and not ints.all () == np.zeros (floats.size).all () :
read_out [a] = ints
else :
read_out [a] = floats
# from *.json; the dict should be written into the file as onto the command line.
elif 'json' in filetype or 'JSON' in filetype :
with open ( path, 'r' ) as f : # alternative 0
read_out = json.load (f) # alternative 0
#f.read ( json.dumps (read_out) ) # alternative 1
# converting the str the their original dtype, determined by what's in the str; better have put it in the file…?
for a in read_out :
if a == 'result' or a == 'datafiles' or a == 'dataid' : # input list of data files which weren't taken into computation yet; absolute paths
pass
elif read_out [a] == '' and 'dir' in a : # Relative paths; set *indir*, *outdir* and *workdir* to *rootpath* if not specified.
read_out [a] = '.'
elif type ( read_out [a] ) == list :
#read_out [a] = pd.read_json ( read_out [a], numpy = True, precise_float = True )
read_out [a] = np.asarray ( read_out [a], dtype = np.float128 )
# from *.txt
elif 'txt' in filetype or 'TXT' in filetype :
with open ( path, 'r' ) as f :
reading = f.read ()
# from *.dat; this shouldn't make a difference for the file here as if saved as *.txt.
elif 'dat' in filetype or 'DAT' in filetype :
with open ( path, 'rb' ) as f :
f.read (read_out)
# Put the variables in the dicts *content* or *hmm*.
for a in read_out :
if 'hmm_' in a :
hmm [a] = read_out [a]
else :
content [a] = read_out [a]
if 'data' in content :
content ['data'] = pd.DataFrame ( content ['data'] )
时将这些文件显示在已更改文件的列表中。
我清楚地将它们添加到/app/src/main/assets/*.json
/app/src/main/assets/*.kt
下，为什么还要在这里再次看到它们？这是我看到的：
git status答案 0 :(得分：1)
问题的根源是无法忽略当前跟踪的文件。
不幸的是，修复需要从索引/暂存区中删除文件（以使它们不被跟踪），这又意味着Git将删除文件从工作树中。您可以使用git rm --cached禁止立即删除此类文件，但是将来，任何回到包含文件的现有提交的人都会将文件放入其索引/临时文件中-area及其工作树，然后从该提交移回到当前提交（不没有文件）意味着Git将删除文件。
也就是说，每当您git checkout提交具有 个文件的提交时，它们都会同时进入您的索引/临时区域（这是同一件事的两个名称）和您的工作-tree（可以在其中查看和使用文件）。每当您从签出这种具有 种提交的文件转移到没有没有这些文件的提交时，Git都会从文件中删除这些文件。索引，并从您的工作树中。因此，这些文件在任何 historyical 中的存在都会有效地使存储库“中毒”。
此问题的唯一完整的解决方案永远不要首先提交文件。这就要求您及时返回并停止提交文件。此解决方案的一种近似方法是重写提交历史记录，以便没有剩余的提交都具有文件：消除所有 did 都具有文件的提交，也许插入新的和改进的替换提交，即没有文件。查看How to make Git "forget" about a file that was tracked but is now in .gitignore?
的许多答案中的一些此解决方案的缺点是提交中不能包含示例原型文件。解决此缺陷的方法是将示例原型文件放入您的提交中，但要使用其他一些文件名：
我有一堆文件不应该受版本控制。但是，如果我不对它们进行版本控制，则构建将失败。由于这些文件包含键/值内容，因此我在其中添加了这些文件，但将实际值替换为伪值。
让您的构建过程使用替代（样本文件）文件代替实际文件进行测试构建。
该软件的用户将使用实际文件，这些文件将不受版本控制。测试版本的用户将使用测试文件，这些文件将受版本控制。
答案 1 :(得分：-1)
您确定将.gitignore文件放在正确的目录中吗？您应将.gitignore放在工作目录中，而不是.git（存储库）目录中