mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
* Introduce first attempt at const-ness
This commit is contained in:
parent
d0d812c548
commit
d70d31aa45
|
@ -18,7 +18,7 @@ cdef class Lexicon:
|
||||||
cpdef readonly StringStore strings
|
cpdef readonly StringStore strings
|
||||||
cdef vector[Lexeme*] lexemes
|
cdef vector[Lexeme*] lexemes
|
||||||
|
|
||||||
cdef Lexeme* get(self, UniStr* s) except NULL
|
cdef const Lexeme* get(self, UniStr* s) except NULL
|
||||||
|
|
||||||
cdef PreshMap _map
|
cdef PreshMap _map
|
||||||
|
|
||||||
|
@ -45,5 +45,5 @@ cdef class Language:
|
||||||
cdef int _find_prefix(self, Py_UNICODE* characters, size_t length) except -1
|
cdef int _find_prefix(self, Py_UNICODE* characters, size_t length) except -1
|
||||||
cdef int _find_suffix(self, Py_UNICODE* characters, size_t length) except -1
|
cdef int _find_suffix(self, Py_UNICODE* characters, size_t length) except -1
|
||||||
cdef int _find_infix(self, Py_UNICODE* characters, size_t length) except -1
|
cdef int _find_infix(self, Py_UNICODE* characters, size_t length) except -1
|
||||||
cdef int _save_cached(self, Lexeme** tokens, hash_t key, int n) except -1
|
cdef int _save_cached(self, const Lexeme* const* tokens, hash_t key, int n) except -1
|
||||||
|
|
||||||
|
|
|
@ -37,11 +37,12 @@ cdef class Language:
|
||||||
self._suffix_re = re.compile(suffix)
|
self._suffix_re = re.compile(suffix)
|
||||||
self._infix_re = re.compile(infix)
|
self._infix_re = re.compile(infix)
|
||||||
self.lexicon = Lexicon(self.set_flags)
|
self.lexicon = Lexicon(self.set_flags)
|
||||||
if path.exists(path.join(util.DATA_DIR, name, 'lexemes')):
|
|
||||||
self.lexicon.load(path.join(util.DATA_DIR, name, 'lexemes'))
|
|
||||||
self.lexicon.strings.load(path.join(util.DATA_DIR, name, 'strings'))
|
|
||||||
self._load_special_tokenization(rules)
|
self._load_special_tokenization(rules)
|
||||||
|
|
||||||
|
def load(self):
|
||||||
|
self.lexicon.load(path.join(util.DATA_DIR, self.name, 'lexemes'))
|
||||||
|
self.lexicon.strings.load(path.join(util.DATA_DIR, self.name, 'strings'))
|
||||||
|
|
||||||
cpdef Tokens tokens_from_list(self, list strings):
|
cpdef Tokens tokens_from_list(self, list strings):
|
||||||
cdef int length = sum([len(s) for s in strings])
|
cdef int length = sum([len(s) for s in strings])
|
||||||
cdef Tokens tokens = Tokens(self.lexicon.strings, length)
|
cdef Tokens tokens = Tokens(self.lexicon.strings, length)
|
||||||
|
@ -84,7 +85,7 @@ cdef class Language:
|
||||||
if Py_UNICODE_ISSPACE(chars[i]) != in_ws:
|
if Py_UNICODE_ISSPACE(chars[i]) != in_ws:
|
||||||
if start < i:
|
if start < i:
|
||||||
slice_unicode(&span, chars, start, i)
|
slice_unicode(&span, chars, start, i)
|
||||||
lexemes = <Lexeme**>self._cache.get(span.key)
|
lexemes = <const Lexeme* const*>self._cache.get(span.key)
|
||||||
if lexemes != NULL:
|
if lexemes != NULL:
|
||||||
tokens.extend(start, lexemes, 0)
|
tokens.extend(start, lexemes, 0)
|
||||||
else:
|
else:
|
||||||
|
@ -96,7 +97,7 @@ cdef class Language:
|
||||||
i += 1
|
i += 1
|
||||||
if start < i:
|
if start < i:
|
||||||
slice_unicode(&span, chars, start, i)
|
slice_unicode(&span, chars, start, i)
|
||||||
lexemes = <Lexeme**>self._cache.get(span.key)
|
lexemes = <const Lexeme* const*>self._cache.get(span.key)
|
||||||
if lexemes != NULL:
|
if lexemes != NULL:
|
||||||
tokens.extend(start, lexemes, 0)
|
tokens.extend(start, lexemes, 0)
|
||||||
else:
|
else:
|
||||||
|
@ -114,8 +115,8 @@ cdef class Language:
|
||||||
self._attach_tokens(tokens, start, span, &prefixes, &suffixes)
|
self._attach_tokens(tokens, start, span, &prefixes, &suffixes)
|
||||||
self._save_cached(&tokens.lex[orig_size], orig_key, tokens.length - orig_size)
|
self._save_cached(&tokens.lex[orig_size], orig_key, tokens.length - orig_size)
|
||||||
|
|
||||||
cdef UniStr* _split_affixes(self, UniStr* string, vector[Lexeme*] *prefixes,
|
cdef UniStr* _split_affixes(self, UniStr* string, vector[const Lexeme*] *prefixes,
|
||||||
vector[Lexeme*] *suffixes) except NULL:
|
vector[const Lexeme*] *suffixes) except NULL:
|
||||||
cdef size_t i
|
cdef size_t i
|
||||||
cdef UniStr prefix
|
cdef UniStr prefix
|
||||||
cdef UniStr suffix
|
cdef UniStr suffix
|
||||||
|
@ -158,17 +159,17 @@ cdef class Language:
|
||||||
|
|
||||||
cdef int _attach_tokens(self, Tokens tokens,
|
cdef int _attach_tokens(self, Tokens tokens,
|
||||||
int idx, UniStr* string,
|
int idx, UniStr* string,
|
||||||
vector[Lexeme*] *prefixes,
|
vector[const Lexeme*] *prefixes,
|
||||||
vector[Lexeme*] *suffixes) except -1:
|
vector[const Lexeme*] *suffixes) except -1:
|
||||||
cdef int split
|
cdef int split
|
||||||
cdef Lexeme** lexemes
|
cdef const Lexeme* const* lexemes
|
||||||
cdef Lexeme* lexeme
|
cdef Lexeme* lexeme
|
||||||
cdef UniStr span
|
cdef UniStr span
|
||||||
if prefixes.size():
|
if prefixes.size():
|
||||||
idx = tokens.extend(idx, prefixes.data(), prefixes.size())
|
idx = tokens.extend(idx, prefixes.data(), prefixes.size())
|
||||||
if string.n != 0:
|
if string.n != 0:
|
||||||
|
|
||||||
lexemes = <Lexeme**>self._cache.get(string.key)
|
lexemes = <const Lexeme* const*>self._cache.get(string.key)
|
||||||
if lexemes != NULL:
|
if lexemes != NULL:
|
||||||
idx = tokens.extend(idx, lexemes, 0)
|
idx = tokens.extend(idx, lexemes, 0)
|
||||||
else:
|
else:
|
||||||
|
@ -182,13 +183,13 @@ cdef class Language:
|
||||||
idx = tokens.push_back(idx, self.lexicon.get(&span))
|
idx = tokens.push_back(idx, self.lexicon.get(&span))
|
||||||
slice_unicode(&span, string.chars, split + 1, string.n)
|
slice_unicode(&span, string.chars, split + 1, string.n)
|
||||||
idx = tokens.push_back(idx, self.lexicon.get(&span))
|
idx = tokens.push_back(idx, self.lexicon.get(&span))
|
||||||
cdef vector[Lexeme*].reverse_iterator it = suffixes.rbegin()
|
cdef vector[const Lexeme*].reverse_iterator it = suffixes.rbegin()
|
||||||
while it != suffixes.rend():
|
while it != suffixes.rend():
|
||||||
idx = tokens.push_back(idx, deref(it))
|
idx = tokens.push_back(idx, deref(it))
|
||||||
preinc(it)
|
preinc(it)
|
||||||
|
|
||||||
cdef int _save_cached(self, Lexeme** tokens, hash_t key, int n) except -1:
|
cdef int _save_cached(self, const Lexeme* const* tokens, hash_t key, int n) except -1:
|
||||||
lexemes = <Lexeme**>self.mem.alloc(n + 1, sizeof(Lexeme**))
|
lexemes = <const Lexeme**>self.mem.alloc(n + 1, sizeof(Lexeme**))
|
||||||
cdef int i
|
cdef int i
|
||||||
for i in range(n):
|
for i in range(n):
|
||||||
lexemes[i] = tokens[i]
|
lexemes[i] = tokens[i]
|
||||||
|
@ -249,7 +250,7 @@ cdef class Lexicon:
|
||||||
self.size = 1
|
self.size = 1
|
||||||
self.set_flags = set_flags
|
self.set_flags = set_flags
|
||||||
|
|
||||||
cdef Lexeme* get(self, UniStr* string) except NULL:
|
cdef const Lexeme* get(self, UniStr* string) except NULL:
|
||||||
'''Retrieve a pointer to a Lexeme from the lexicon.'''
|
'''Retrieve a pointer to a Lexeme from the lexicon.'''
|
||||||
cdef Lexeme* lex
|
cdef Lexeme* lex
|
||||||
lex = <Lexeme*>self._map.get(string.key)
|
lex = <Lexeme*>self._map.get(string.key)
|
||||||
|
@ -289,14 +290,14 @@ cdef class Lexicon:
|
||||||
return self.lexemes.at(id_or_string)[0]
|
return self.lexemes.at(id_or_string)[0]
|
||||||
cdef UniStr string
|
cdef UniStr string
|
||||||
slice_unicode(&string, id_or_string, 0, len(id_or_string))
|
slice_unicode(&string, id_or_string, 0, len(id_or_string))
|
||||||
cdef Lexeme* lexeme = self.get(&string)
|
cdef const Lexeme* lexeme = self.get(&string)
|
||||||
return lexeme[0]
|
return lexeme[0]
|
||||||
|
|
||||||
def __setitem__(self, unicode uni_string, dict props):
|
def __setitem__(self, unicode uni_string, dict props):
|
||||||
cdef UniStr s
|
cdef UniStr s
|
||||||
slice_unicode(&s, uni_string, 0, len(uni_string))
|
slice_unicode(&s, uni_string, 0, len(uni_string))
|
||||||
cdef Lexeme* lex = self.get(&s)
|
cdef const Lexeme* lex = self.get(&s)
|
||||||
lex[0] = lexeme_init(lex.id, s.chars[:s.n], s.key, self.strings, props)
|
self.lexemes[lex.id][0] = lexeme_init(lex.id, s.chars[:s.n], s.key, self.strings, props)
|
||||||
|
|
||||||
def dump(self, loc):
|
def dump(self, loc):
|
||||||
if path.exists(loc):
|
if path.exists(loc):
|
||||||
|
@ -319,7 +320,8 @@ cdef class Lexicon:
|
||||||
assert st == 0
|
assert st == 0
|
||||||
|
|
||||||
def load(self, loc):
|
def load(self, loc):
|
||||||
assert path.exists(loc)
|
if not path.exists(loc):
|
||||||
|
raise IOError('Lexemes file not found at %s' % loc)
|
||||||
cdef bytes bytes_loc = loc.encode('utf8') if type(loc) == unicode else loc
|
cdef bytes bytes_loc = loc.encode('utf8') if type(loc) == unicode else loc
|
||||||
cdef FILE* fp = fopen(<char*>bytes_loc, 'rb')
|
cdef FILE* fp = fopen(<char*>bytes_loc, 'rb')
|
||||||
assert fp != NULL
|
assert fp != NULL
|
||||||
|
|
|
@ -112,8 +112,8 @@ cpdef Lexeme init(id_t i, unicode string, hash_t hashed, StringStore store,
|
||||||
dict props) except *
|
dict props) except *
|
||||||
|
|
||||||
|
|
||||||
cdef inline bint check_flag(Lexeme* lexeme, attr_id_t flag_id) nogil:
|
cdef inline bint check_flag(const Lexeme* lexeme, attr_id_t flag_id) nogil:
|
||||||
return lexeme.flags & (1 << flag_id)
|
return lexeme.flags & (1 << flag_id)
|
||||||
|
|
||||||
|
|
||||||
cdef attr_t get_attr(Lexeme* lex, attr_id_t attr_id)
|
cdef attr_t get_attr(const Lexeme* lex, attr_id_t attr_id)
|
||||||
|
|
|
@ -35,7 +35,7 @@ cpdef Lexeme init(id_t i, unicode string, hash_t hashed,
|
||||||
return lex
|
return lex
|
||||||
|
|
||||||
|
|
||||||
cdef attr_t get_attr(Lexeme* lex, attr_id_t feat_name):
|
cdef attr_t get_attr(const Lexeme* lex, attr_id_t feat_name):
|
||||||
if feat_name < (sizeof(flags_t) * 8):
|
if feat_name < (sizeof(flags_t) * 8):
|
||||||
return check_flag(lex, feat_name)
|
return check_flag(lex, feat_name)
|
||||||
elif feat_name == ID:
|
elif feat_name == ID:
|
||||||
|
|
|
@ -14,11 +14,11 @@ cdef class Tokens:
|
||||||
cdef Pool mem
|
cdef Pool mem
|
||||||
cdef StringStore _string_store
|
cdef StringStore _string_store
|
||||||
|
|
||||||
cdef Lexeme** _lex_ptr
|
cdef const Lexeme** _lex_ptr
|
||||||
cdef int* _idx_ptr
|
cdef int* _idx_ptr
|
||||||
cdef int* _pos_ptr
|
cdef int* _pos_ptr
|
||||||
cdef int* _ner_ptr
|
cdef int* _ner_ptr
|
||||||
cdef Lexeme** lex
|
cdef const Lexeme** lex
|
||||||
cdef int* idx
|
cdef int* idx
|
||||||
cdef int* pos
|
cdef int* pos
|
||||||
cdef int* ner
|
cdef int* ner
|
||||||
|
@ -26,8 +26,8 @@ cdef class Tokens:
|
||||||
cdef int length
|
cdef int length
|
||||||
cdef int max_length
|
cdef int max_length
|
||||||
|
|
||||||
cdef int extend(self, int i, Lexeme** lexemes, int n) except -1
|
cdef int extend(self, int i, const Lexeme* const* lexemes, int n) except -1
|
||||||
cdef int push_back(self, int i, Lexeme* lexeme) except -1
|
cdef int push_back(self, int i, const Lexeme* lexeme) except -1
|
||||||
cpdef int set_tag(self, int i, int tag_type, int tag) except -1
|
cpdef int set_tag(self, int i, int tag_type, int tag) except -1
|
||||||
|
|
||||||
cpdef np.ndarray[atom_t, ndim=2] get_array(self, list features)
|
cpdef np.ndarray[atom_t, ndim=2] get_array(self, list features)
|
||||||
|
|
|
@ -44,7 +44,7 @@ cdef class Tokens:
|
||||||
# Guarantee self.lex[i-x], for any i >= 0 and x < padding is in bounds
|
# Guarantee self.lex[i-x], for any i >= 0 and x < padding is in bounds
|
||||||
# However, we need to remember the true starting places, so that we can
|
# However, we need to remember the true starting places, so that we can
|
||||||
# realloc.
|
# realloc.
|
||||||
self._lex_ptr = <Lexeme**>self.mem.alloc(size + (PADDING*2), sizeof(Lexeme*))
|
self._lex_ptr = <const Lexeme**>self.mem.alloc(size + (PADDING*2), sizeof(Lexeme*))
|
||||||
self._idx_ptr = <int*>self.mem.alloc(size + (PADDING*2), sizeof(int))
|
self._idx_ptr = <int*>self.mem.alloc(size + (PADDING*2), sizeof(int))
|
||||||
self._pos_ptr = <int*>self.mem.alloc(size + (PADDING*2), sizeof(int))
|
self._pos_ptr = <int*>self.mem.alloc(size + (PADDING*2), sizeof(int))
|
||||||
self._ner_ptr = <int*>self.mem.alloc(size + (PADDING*2), sizeof(int))
|
self._ner_ptr = <int*>self.mem.alloc(size + (PADDING*2), sizeof(int))
|
||||||
|
@ -74,7 +74,7 @@ cdef class Tokens:
|
||||||
def __len__(self):
|
def __len__(self):
|
||||||
return self.length
|
return self.length
|
||||||
|
|
||||||
cdef int push_back(self, int idx, Lexeme* lexeme) except -1:
|
cdef int push_back(self, int idx, const Lexeme* lexeme) except -1:
|
||||||
if self.length == self.max_length:
|
if self.length == self.max_length:
|
||||||
self._realloc(self.length * 2)
|
self._realloc(self.length * 2)
|
||||||
self.lex[self.length] = lexeme
|
self.lex[self.length] = lexeme
|
||||||
|
@ -84,7 +84,7 @@ cdef class Tokens:
|
||||||
self.length += 1
|
self.length += 1
|
||||||
return idx + lexeme.length
|
return idx + lexeme.length
|
||||||
|
|
||||||
cdef int extend(self, int idx, Lexeme** lexemes, int n) except -1:
|
cdef int extend(self, int idx, const Lexeme* const* lexemes, int n) except -1:
|
||||||
cdef int i
|
cdef int i
|
||||||
if lexemes == NULL:
|
if lexemes == NULL:
|
||||||
return idx
|
return idx
|
||||||
|
@ -116,7 +116,7 @@ cdef class Tokens:
|
||||||
def _realloc(self, new_size):
|
def _realloc(self, new_size):
|
||||||
self.max_length = new_size
|
self.max_length = new_size
|
||||||
n = new_size + (PADDING * 2)
|
n = new_size + (PADDING * 2)
|
||||||
self._lex_ptr = <Lexeme**>self.mem.realloc(self._lex_ptr, n * sizeof(Lexeme*))
|
self._lex_ptr = <const Lexeme**>self.mem.realloc(self._lex_ptr, n * sizeof(Lexeme*))
|
||||||
self._idx_ptr = <int*>self.mem.realloc(self._idx_ptr, n * sizeof(int))
|
self._idx_ptr = <int*>self.mem.realloc(self._idx_ptr, n * sizeof(int))
|
||||||
self._pos_ptr = <int*>self.mem.realloc(self._pos_ptr, n * sizeof(int))
|
self._pos_ptr = <int*>self.mem.realloc(self._pos_ptr, n * sizeof(int))
|
||||||
self._ner_ptr = <int*>self.mem.realloc(self._ner_ptr, n * sizeof(int))
|
self._ner_ptr = <int*>self.mem.realloc(self._ner_ptr, n * sizeof(int))
|
||||||
|
|
Loading…
Reference in New Issue
Block a user