Fix stupid bug with ignore-case
This commit is contained in:
parent
3a75db3b49
commit
d0dd2cff17
21
README.md
21
README.md
@ -6,20 +6,21 @@ Then this is for you...
|
|||||||
|
|
||||||
## What is this?
|
## What is this?
|
||||||
|
|
||||||
`crapgrep` is a poor imitation of the Unix utility `grep` written in Python.
|
`crapgrep` is a poor imitation of the Unix utility `grep`, written in Python.
|
||||||
|
|
||||||
More specifically, it's a command line tool to search for a pattern or a substring in each line of one or more text files.
|
More specifically, it's a command line tool to search for a pattern or a substring in each line of one or more text files.
|
||||||
|
|
||||||
The command synopsis is very similar to `grep`, although it needs the Python interpreter to be invoked explicitly (at the moment, at least):
|
The command synopsis is very similar to `grep`'s, although it needs the Python interpreter to be invoked explicitly (at the moment, at least):
|
||||||
|
|
||||||
```
|
```
|
||||||
python crapgrep.py [OPTIONS] [PATTERN] [FILE[...]]
|
python crapgrep.py [OPTION...] [PATTERN] [FILE...]
|
||||||
```
|
```
|
||||||
|
|
||||||
_**Note**: obviously, `crapgrep` doesn't read from `stdin`, which makes it even more useless..._
|
> _**Note**: obviously, `crapgrep` doesn't read from `stdin`, which makes it even more useless..._
|
||||||
|
|
||||||
## Installation
|
## Installation
|
||||||
|
|
||||||
If you like wasting time because apparently you have nothing better to do, you can try `crapgrep` by cloning the repository with `git`:
|
If you like wasting time (because apparently you have nothing better to do), you can try `crapgrep` by cloning the repository with `git`:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
git clone https://baltig.cnr.it/nicolo.paraciani/crapgrep.git
|
git clone https://baltig.cnr.it/nicolo.paraciani/crapgrep.git
|
||||||
@ -28,8 +29,8 @@ git clone https://baltig.cnr.it/nicolo.paraciani/crapgrep.git
|
|||||||
then
|
then
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
cd crapgrep
|
cd crapgrep/crapgrep
|
||||||
python crapgrep.py <option> <file(s)>
|
python crapgrep.py <options> <files>
|
||||||
```
|
```
|
||||||
|
|
||||||
## Examples
|
## Examples
|
||||||
@ -44,15 +45,15 @@ Searching for the simple string `'hola'` in file `garbage.txt` in the current di
|
|||||||
python crapgrep.py hola garbage.txt
|
python crapgrep.py hola garbage.txt
|
||||||
```
|
```
|
||||||
|
|
||||||
To make the search case-insensitive, you could do:
|
To make the search case-insensitive:
|
||||||
|
|
||||||
```
|
```
|
||||||
python crapgrep.py -i hOlA garbage.txt
|
python crapgrep.py -i hola garbage.txt
|
||||||
```
|
```
|
||||||
|
|
||||||
### Regexp
|
### Regexp
|
||||||
|
|
||||||
_**Note**: unlike `grep`, `crapgrep` doesn't treat the string as a regular expression pattern by default, it must be specified by passing the `-E` option explicitly._
|
_**Note**: unlike `grep`, `crapgrep` doesn't treat the pattern as a regular expression by default, it must be specified by passing the `-E` option explicitly._
|
||||||
|
|
||||||
Searching for pattern `'^urka[0-9]'` in files `garbage1.txt` and `garbage2.txt` in the parent directory:
|
Searching for pattern `'^urka[0-9]'` in files `garbage1.txt` and `garbage2.txt` in the parent directory:
|
||||||
|
|
||||||
|
@ -2,11 +2,9 @@ import exceptions
|
|||||||
import re
|
import re
|
||||||
import os
|
import os
|
||||||
import sys
|
import sys
|
||||||
import sty
|
|
||||||
|
|
||||||
|
|
||||||
# TODO Avoid extra fname argument??
|
def find_line(line: str, pattern: str, i_case: bool, is_regexp=False) -> bool:
|
||||||
def find_line(line: str, pattern: str, is_regexp=False) -> bool:
|
|
||||||
"""
|
"""
|
||||||
Distinguish between regexp or not (default is False)
|
Distinguish between regexp or not (default is False)
|
||||||
"""
|
"""
|
||||||
@ -16,6 +14,9 @@ def find_line(line: str, pattern: str, is_regexp=False) -> bool:
|
|||||||
if is_regexp:
|
if is_regexp:
|
||||||
matches = re.findall(pattern, line)
|
matches = re.findall(pattern, line)
|
||||||
FIND_COND = len(matches) > 0
|
FIND_COND = len(matches) > 0
|
||||||
|
elif i_case:
|
||||||
|
lower = line.lower()
|
||||||
|
FIND_COND = lower.find(pattern.lower()) != -1
|
||||||
else:
|
else:
|
||||||
FIND_COND = line.find(pattern) != -1
|
FIND_COND = line.find(pattern) != -1
|
||||||
|
|
||||||
@ -93,7 +94,7 @@ def parse_args(args: list) -> dict:
|
|||||||
# TODO does it make sense?
|
# TODO does it make sense?
|
||||||
for opt in options:
|
for opt in options:
|
||||||
if opt not in OPTS:
|
if opt not in OPTS:
|
||||||
raise exceptions.InvalidOption(opt[1:])
|
raise exceptions.InvalidOptionError(opt)
|
||||||
|
|
||||||
args_tree["options"] = options
|
args_tree["options"] = options
|
||||||
|
|
||||||
@ -113,22 +114,13 @@ def parse_args(args: list) -> dict:
|
|||||||
return args_tree
|
return args_tree
|
||||||
|
|
||||||
|
|
||||||
def match_regexp(pattern: str, line: str) -> object:
|
|
||||||
"""
|
|
||||||
Search for pattern in the given line and return
|
|
||||||
a match object or None if no match found.
|
|
||||||
|
|
||||||
Flags??
|
|
||||||
"""
|
|
||||||
return re.search(pattern, line)
|
|
||||||
|
|
||||||
|
|
||||||
def process_grep(args_tree: dict) -> list:
|
def process_grep(args_tree: dict) -> list:
|
||||||
lines = []
|
lines = []
|
||||||
found_lines = []
|
found_lines = []
|
||||||
options = args_tree["options"]
|
options = args_tree["options"]
|
||||||
pattern = args_tree["pattern"]
|
pattern = args_tree["pattern"]
|
||||||
files = args_tree["files"]
|
files = args_tree["files"]
|
||||||
|
i_case = False
|
||||||
|
|
||||||
try:
|
try:
|
||||||
for f in files:
|
for f in files:
|
||||||
@ -139,19 +131,19 @@ def process_grep(args_tree: dict) -> list:
|
|||||||
|
|
||||||
n = 0
|
n = 0
|
||||||
|
|
||||||
# Check if case insensitive
|
|
||||||
if 'i' in options:
|
|
||||||
pattern = pattern.lower()
|
|
||||||
for line in lines:
|
for line in lines:
|
||||||
n = n + 1
|
n = n + 1
|
||||||
|
# Check if case insensitive
|
||||||
|
if 'i' in options:
|
||||||
|
i_case = True
|
||||||
# Check if regexp flag
|
# Check if regexp flag
|
||||||
if 'E' in options:
|
if 'E' in options:
|
||||||
# pattern is regexp
|
# pattern is regexp
|
||||||
if not check_pattern(pattern):
|
if not check_pattern(pattern):
|
||||||
raise exceptions.InvalidPattern(pattern)
|
raise exceptions.InvalidPatternError(pattern)
|
||||||
found = find_line(line, pattern, True)
|
found = find_line(line, pattern, i_case, True)
|
||||||
else:
|
else:
|
||||||
found = find_line(line, pattern)
|
found = find_line(line, pattern, i_case)
|
||||||
|
|
||||||
lnum = str(n) + ':' if 'n' in options else ''
|
lnum = str(n) + ':' if 'n' in options else ''
|
||||||
|
|
||||||
@ -175,7 +167,7 @@ if __name__ == "__main__":
|
|||||||
|
|
||||||
try:
|
try:
|
||||||
args_tree = parse_args(args)
|
args_tree = parse_args(args)
|
||||||
except exceptions.InvalidOption as e:
|
except exceptions.InvalidOptionError as e:
|
||||||
print(e.get_message())
|
print(e.get_message())
|
||||||
print_usage()
|
print_usage()
|
||||||
sys.exit(1)
|
sys.exit(1)
|
||||||
@ -183,6 +175,6 @@ if __name__ == "__main__":
|
|||||||
try:
|
try:
|
||||||
for line in process_grep(args_tree):
|
for line in process_grep(args_tree):
|
||||||
print(line)
|
print(line)
|
||||||
except exceptions.InvalidPattern as e:
|
except exceptions.InvalidPatternError as e:
|
||||||
print(e.get_message())
|
print(e.get_message())
|
||||||
sys.exit(1)
|
sys.exit(1)
|
||||||
|
@ -1,4 +1,4 @@
|
|||||||
class InvalidOption(Exception):
|
class InvalidOptionError(Exception):
|
||||||
def __init__(self, invalid_opt):
|
def __init__(self, invalid_opt):
|
||||||
self.invalid_opt = invalid_opt
|
self.invalid_opt = invalid_opt
|
||||||
|
|
||||||
@ -6,7 +6,7 @@ class InvalidOption(Exception):
|
|||||||
return f"crapgrep: invalid option -- '{self.invalid_opt}'"
|
return f"crapgrep: invalid option -- '{self.invalid_opt}'"
|
||||||
|
|
||||||
|
|
||||||
class InvalidPattern(Exception):
|
class InvalidPatternError(Exception):
|
||||||
def __init__(self, pattern):
|
def __init__(self, pattern):
|
||||||
self.invalid = pattern
|
self.invalid = pattern
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user