def test_intermix_just_required_args_and_implicit_stdin(self):
infile = StringIO("a,b,c\n1,2,3\n")
with stdin_as_string(infile):
self.assertLines(
[
r"(\w)",
r"\1!",
],
[
"a,b,c",
"1!,2!,3!",
],
)
infile.close()
# -c option in the middle of stuff
infile = StringIO("a,b,c\n1,2,3\n")
with stdin_as_string(infile):
self.assertLines(
[
r"(\w)",
r"\1!",
"-c",
"a,c",
],
[
"a,b,c",
"1!,2,3!",
],
)
infile.close()
def test_filtered_columns(self):
"""only selected columns are affected, AND filtered for"""
with stdin_as_string(self.idata):
self.assertLines(
[
"-F",
"-c",
"id,name",
r"([3-9])",
r"\1@",
],
[
"id,name,val",
"3@,4@,5",
"6@,7@y,8z",
],
)
# variation...
with stdin_as_string(self.idata):
self.assertLines(
[
"-Fc",
"2",
r"[a-z]",
r"$",
],
[
"id,name,val",
"6,7$,8z",
],
)
def test_slugify(self):
input_file = StringIO(
'id, Hello ,World\nBond,Good-bye!,"E A R T H\n Ling!"')
with stdin_as_string(input_file):
self.assertLines(
[
"--slugify",
],
[
"id, Hello ,World",
"bond,good_bye,e_a_r_t_h_ling",
],
)
# verify alias works
with stdin_as_string(StringIO("a,b,c\nD-D, E?E, !F! \n")):
self.assertLines(
[
"-S",
],
[
"a,b,c",
"d_d,e_e,f",
],
)
def test_slugify_overrides_lower_and_upper(self):
"""
makes no sense for user to specify both slugify and upper/lower. But if they do, we silently handle it,
as slugify's effects overrides lower/upper
"""
with stdin_as_string(self.ifile):
self.assertLines(
[
"-U",
"-S",
],
[
"A,B,C",
"hello,wor_ld,good_bye",
],
)
with stdin_as_string(self.ifile):
self.assertLines(
[
"-L",
"-S",
],
[
"A,B,C",
"hello,wor_ld,good_bye",
],
)
def test_single_index(self):
with stdin_as_string(self.ifile):
self.assertLines(
["-i", "0"],
["id", "0"],
)
with stdin_as_string(self.ifile):
self.assertLines(
["--indexes", "9"],
["id", "9"],
)
def test_columns_by_index(self):
"""only specified columns are affected"""
with stdin_as_string(self.idata):
self.assertLines(
["-c", "3,1", r"(\w+)", r"\1!"],
["id,name,val", "1!,2,3x!", "3!,4,5!", "6!,7y,8z!"],
)
def test_add_craploads_of_headers(self):
txt = ",".join(str(i) for i in range(100))
infile = StringIO(f"{txt}\n")
with stdin_as_string(infile):
self.assertLines(
["-G"],
[",".join(f"field_{i}" for i in range(1, 101)), txt],
)
infile.close()
def test_opts_then_args(self, opts):
with stdin_as_string(self.indata):
self.assertLines(
[
*opts,
*self.margs,
],
self.answer,
)
def test_squeeze_then_strip(self):
with stdin_as_string(self.ifile):
self.assertLines(
[],
[
"a,b,c",
"1,2 2,3",
],
)
def test_slugify_intro_example(self):
with stdin_as_string(self.idata):
self.assertLines(
["-S"],
[
"case,x,y,i_d",
"1,2,3,4",
"5,6,7,8",
],
)
def test_rename_intro_example(self):
with stdin_as_string(self.idata):
self.assertLines(
["-R", "1|Case Num,4|ID,X|lat,Y|lng"],
[
"Case Num,lat,lng,ID",
"1,2,3,4",
"5,6,7,8",
],
)
def test_start_equals_end_is_fine(self):
"""why would user do this, who knows, but it's technically fine"""
with stdin_as_string(self.ifile):
self.assertLines(
["-i", "0-0"],
[
"id",
"0",
],
)
with stdin_as_string(self.ifile):
self.assertLines(
["-i", "3-3"],
[
"id",
"3",
],
)
def test_several_indexes(self):
with stdin_as_string(self.ifile):
self.assertLines(
["-i", "2,0,9,2"],
[
"id",
"0",
"2",
"9",
],
)
def test_lower_bound(self):
with stdin_as_string(self.ifile):
self.assertLines(
["-i", "7-"],
[
"id",
"7",
"8",
"9",
],
)
def test_babynames_create_header(self):
with stdin_as_string(self.idata):
self.assertLines(
["-A", "name,sex,count"],
[
"name,sex,count",
"Mary,F,7065",
"Anna,F,2604",
"Emma,F,2003",
],
)
def test_uppercase(self):
input_file = StringIO("a,b,c\nHello,World !,Good-Bye\n")
with stdin_as_string(input_file):
self.assertLines(
[
"--uppercase",
],
["a,b,c", "HELLO,WORLD !,GOOD-BYE"],
)
with stdin_as_string(StringIO("a,b,c\nd,e,f\n")):
self.assertLines(
[
"-U",
],
[
"a,b,c",
"D,E,F",
],
)
def test_lowercase(self):
input_file = StringIO("A,B,C\nHello,World !,Good-Bye\n")
with stdin_as_string(input_file):
self.assertLines(
[
"--lowercase",
],
["A,B,C", "hello,world !,good-bye"],
)
with stdin_as_string(StringIO("A,B,C\nD,E,F\n")):
self.assertLines(
[
"-L",
],
[
"A,B,C",
"d,e,f",
],
)
def test_intro(self):
data = StringIO("id,val\n0,a\n1,b\n2,c\n3,d\n")
with stdin_as_string(data):
self.assertLines(
["-i", "0,2-3"],
[
"id,val",
"0,a",
"2,c",
"3,d",
],
)
def test_slugify_helpdoc(self):
ifile = StringIO('APPLES,"Date - Time "\n')
with stdin_as_string(ifile):
self.assertLines(
[
"-S",
],
[
"apples,date_time",
],
)
def test_single_interval(self):
with stdin_as_string(self.ifile):
self.assertLines(
["-i", "3-5"],
[
"id",
"3",
"4",
"5",
],
)
with stdin_as_string(self.ifile):
self.assertLines(
["-i", "8-10000"],
[
"id",
"8",
"9",
],
)
def test_selective_norming(self):
with stdin_as_string(self.ifile):
self.assertLines(
[
"-c",
"2-3",
],
[
"a,b,c,d",
"hello,World,and Good?, bye ! ",
],
)
def test_selective_slugifying(self):
with stdin_as_string(self.ifile):
self.assertLines(
[
"--columns",
"b,c",
"-S",
],
[
"a,b,c,d",
"hello,world,and_good, bye ! ",
],
)
def test_zero_range(self):
"""0 can be a special case because sometimes I forget how Python treats 0 as falsy/nonetype"""
with stdin_as_string(self.ifile):
self.assertLines(
["-i", "0-3"],
[
"id",
"0",
"1",
"2",
"3",
],
)
def test_usage_filter_example(self):
"""
$ csvsed -F '[a-z]' '%' data.csv
"""
with stdin_as_string(self.idata):
self.assertLines(
[
"-F",
"[a-z]",
"%",
],
["id,name,val", "1,2,3%", "6,7%,8%"],
)
def test_supports_case_insensitivity(self):
tdata = "\n".join(["a,b,c,d", "hey,Hello,hat,hEx"])
with stdin_as_string(StringIO(tdata)):
self.assertLines(
[
"(?i)h(?=e)",
"M",
],
[
"a,b,c,d",
"Mey,Mello,hat,MEx",
],
)
def test_keep_lines(self):
r"""--keep-lines prevents squeeze's default conversion of \n to ' '"""
input_file = StringIO('a, b ,c\n11,2 2,"3 \n\n 3"')
with stdin_as_string(input_file):
self.assertLines(
[
"--keep-lines",
],
[
"a, b ,c",
'11,2 2,"3 ',
' 3"',
],
)
def test_squeezing(self):
"""
consecutive whitespace and newlines \n are collapsed
(and stripping is applied)
"""
input_file = StringIO('a, b ,c\n11,2 2,"3 \n\n 3"')
with stdin_as_string(input_file):
self.assertLines(
[],
[
"a, b ,c",
"11,2 2,3 3",
],
)
def test_edgy_lower_bound(self):
"""
for now, we don't warn user if there are overlapping/conflicting bounds
"""
with stdin_as_string(self.ifile):
self.assertLines(
["-i", "9-,8,9,7-,8-"],
[
"id",
"7",
"8",
"9",
],
)
def test_intro(self):
datacsv = StringIO("id,name\n1,Mrs. Adams\n2,Miss Miller\n3,Mrs Smith\n")
with stdin_as_string(datacsv):
self.assertLines(
[
r"(Mrs|Miss|Ms)\.?",
"Ms.",
],
[
"id,name",
"1,Ms. Adams",
"2,Ms. Miller",
"3,Ms. Smith",
],
)
def test_default(self):
iof = StringIO("a,b,c\n0,12345,67890\n")
with stdin_as_string(iof):
self.assertLines(
["--max-length", "3"],
[
"| field | value |",
"| ----- | ----- |",
"| a | 0 |",
"| b | 123 |",
"| | 45 |",
"| c | 678 |",
"| | 90 |",
],
)
