mirror of
https://github.com/ralsina/tartrazine.git
synced 2024-11-13 23:12:24 +00:00
8ff885a3a8
Closes #17 Implements the IsGenerated helper function to filter out generated files using the rules and matchers in: - https://github.com/github/linguist/blob/master/lib/linguist/generated.rb Since the vast majority of matchers have very different logic, it cannot be autogenerated directly from linguist like other logics in enry, so it's translated by hand. There are three different types of matchers in this implementation: - By extension, which mark as generated based only in the extension. These are the fastest matchers, so they're done first. - By file name, which matches patterns against the filename. These are performed in second place. Unlike linguist, we try to use string functions instead of regexps as much as possible. - Finally, the rest of the matchers, which go into the content and try to identify if they're generated or not based on the content. Unlike linguist, we try to only read the content we need and not split it all unless it's necessary and use byte functions instead of regexps as much as possible. Signed-off-by: Miguel Molina <miguel@erizocosmi.co>
95 lines
2.8 KiB
Python
95 lines
2.8 KiB
Python
"""
|
|
Python library calling enry Go implementation trough cFFI (API, out-of-line) and Cgo.
|
|
"""
|
|
|
|
from _c_enry import ffi, lib
|
|
|
|
## cgo -> ffi helpers
|
|
def py_bytes_to_go(py_bytes: bytes):
|
|
c_bytes = ffi.new("char[]", len(py_bytes))
|
|
go_slice = ffi.new("GoSlice *", [c_bytes, len(py_bytes), len(py_bytes)])
|
|
return (go_slice[0], c_bytes)
|
|
|
|
def py_str_to_go(py_str: str):
|
|
str_bytes = py_str.encode()
|
|
c_str = ffi.new("char[]", str_bytes)
|
|
go_str = ffi.new("_GoString_ *", [c_str, len(str_bytes)])
|
|
return (go_str[0], c_str)
|
|
|
|
def go_str_to_py(go_str: str):
|
|
str_len = go_str.n
|
|
if str_len > 0:
|
|
return ffi.unpack(go_str.p, go_str.n).decode()
|
|
return ""
|
|
|
|
def go_bool_to_py(go_bool: bool):
|
|
return go_bool == 1
|
|
|
|
|
|
## API, TODO(bzz): add docstrings
|
|
def language(filename: str, content: bytes) -> str:
|
|
fName, c_str = py_str_to_go(filename)
|
|
fContent, c_bytes = py_bytes_to_go(content)
|
|
guess = lib.GetLanguage(fName, fContent)
|
|
lang = go_str_to_py(guess)
|
|
return lang
|
|
|
|
def language_by_extension(filename: str) -> str:
|
|
fName, c_str = py_str_to_go(filename)
|
|
guess = lib.GetLanguageByExtension(fName)
|
|
lang = go_str_to_py(guess.r0)
|
|
return lang
|
|
|
|
def language_by_filename(filename: str) -> str:
|
|
fName, c_str = py_str_to_go(filename)
|
|
guess = lib.GetLanguageByFilename(fName)
|
|
lang = go_str_to_py(guess.r0)
|
|
return lang
|
|
|
|
def is_vendor(filename: str) -> bool:
|
|
fName, c_str = py_str_to_go(filename)
|
|
guess = lib.IsVendor(fName)
|
|
return go_bool_to_py(guess)
|
|
|
|
def is_generated(filename: str, content: bytes) -> bool:
|
|
fname, c_str = py_str_to_go(filename)
|
|
fcontent, c_bytes = py_bytes_to_go(content)
|
|
guess = lib.IsGenerated(fname, fcontent)
|
|
return go_bool_to_py(guess)
|
|
|
|
|
|
## Tests
|
|
from collections import namedtuple
|
|
|
|
def main():
|
|
TestFile = namedtuple("TestFile", "name, content, lang")
|
|
files = [
|
|
TestFile("Parse.hs", b"", "Haskell"), TestFile("some.cpp", b"", "C++"),
|
|
TestFile("orand.go", b"", "Go"), TestFile("type.h", b"", "C"),
|
|
TestFile(".bashrc", b"", "Shell"), TestFile(".gitignore", b"", "Ignore List")
|
|
]
|
|
|
|
print("\nstrategy: extension")
|
|
for f in files:
|
|
lang = language_by_extension(f.name)
|
|
print("\tfile: {:10s} language: '{}'".format(f.name, lang))
|
|
|
|
print("\nstrategy: filename")
|
|
for f in files:
|
|
lang = language_by_filename(f.name)
|
|
print("\tfile: {:10s} language: '{}'".format(f.name, lang))
|
|
|
|
print("\ncheck: is vendor?")
|
|
for f in files:
|
|
vendor = is_vendor(f.name)
|
|
print("\tfile: {:10s} vendor: '{}'".format(f.name, vendor))
|
|
|
|
print("\nstrategy: all")
|
|
for f in files:
|
|
lang = language(f.name, f.content)
|
|
print("\tfile: {:10s} language: '{}'".format(f.name, lang))
|
|
assert lang == f.lang, "Expected '{}' but got '{}'".format(f.lang, lang)
|
|
|
|
if __name__ == "__main__":
|
|
main()
|