Show More
@@ -1,1174 +1,1174 b'' | |||||
1 | /* |
|
1 | /* | |
2 | parsers.c - efficient content parsing |
|
2 | parsers.c - efficient content parsing | |
3 |
|
3 | |||
4 | Copyright 2008 Olivia Mackall <olivia@selenic.com> and others |
|
4 | Copyright 2008 Olivia Mackall <olivia@selenic.com> and others | |
5 |
|
5 | |||
6 | This software may be used and distributed according to the terms of |
|
6 | This software may be used and distributed according to the terms of | |
7 | the GNU General Public License, incorporated herein by reference. |
|
7 | the GNU General Public License, incorporated herein by reference. | |
8 | */ |
|
8 | */ | |
9 |
|
9 | |||
10 | #define PY_SSIZE_T_CLEAN |
|
10 | #define PY_SSIZE_T_CLEAN | |
11 | #include <Python.h> |
|
11 | #include <Python.h> | |
12 | #include <ctype.h> |
|
12 | #include <ctype.h> | |
13 | #include <stddef.h> |
|
13 | #include <stddef.h> | |
14 | #include <string.h> |
|
14 | #include <string.h> | |
15 |
|
15 | |||
16 | #include "bitmanipulation.h" |
|
16 | #include "bitmanipulation.h" | |
17 | #include "charencode.h" |
|
17 | #include "charencode.h" | |
18 | #include "util.h" |
|
18 | #include "util.h" | |
19 |
|
19 | |||
20 | #ifdef IS_PY3K |
|
20 | #ifdef IS_PY3K | |
21 | /* The mapping of Python types is meant to be temporary to get Python |
|
21 | /* The mapping of Python types is meant to be temporary to get Python | |
22 | * 3 to compile. We should remove this once Python 3 support is fully |
|
22 | * 3 to compile. We should remove this once Python 3 support is fully | |
23 | * supported and proper types are used in the extensions themselves. */ |
|
23 | * supported and proper types are used in the extensions themselves. */ | |
24 | #define PyInt_Check PyLong_Check |
|
24 | #define PyInt_Check PyLong_Check | |
25 | #define PyInt_FromLong PyLong_FromLong |
|
25 | #define PyInt_FromLong PyLong_FromLong | |
26 | #define PyInt_FromSsize_t PyLong_FromSsize_t |
|
26 | #define PyInt_FromSsize_t PyLong_FromSsize_t | |
27 | #define PyInt_AsLong PyLong_AsLong |
|
27 | #define PyInt_AsLong PyLong_AsLong | |
28 | #endif |
|
28 | #endif | |
29 |
|
29 | |||
30 | static const char *const versionerrortext = "Python minor version mismatch"; |
|
30 | static const char *const versionerrortext = "Python minor version mismatch"; | |
31 |
|
31 | |||
32 | static const int dirstate_v1_from_p2 = -2; |
|
32 | static const int dirstate_v1_from_p2 = -2; | |
33 | static const int dirstate_v1_nonnormal = -1; |
|
33 | static const int dirstate_v1_nonnormal = -1; | |
34 | static const int ambiguous_time = -1; |
|
34 | static const int ambiguous_time = -1; | |
35 |
|
35 | |||
36 | static PyObject *dict_new_presized(PyObject *self, PyObject *args) |
|
36 | static PyObject *dict_new_presized(PyObject *self, PyObject *args) | |
37 | { |
|
37 | { | |
38 | Py_ssize_t expected_size; |
|
38 | Py_ssize_t expected_size; | |
39 |
|
39 | |||
40 | if (!PyArg_ParseTuple(args, "n:make_presized_dict", &expected_size)) { |
|
40 | if (!PyArg_ParseTuple(args, "n:make_presized_dict", &expected_size)) { | |
41 | return NULL; |
|
41 | return NULL; | |
42 | } |
|
42 | } | |
43 |
|
43 | |||
44 | return _dict_new_presized(expected_size); |
|
44 | return _dict_new_presized(expected_size); | |
45 | } |
|
45 | } | |
46 |
|
46 | |||
47 | static PyObject *dirstate_item_new(PyTypeObject *subtype, PyObject *args, |
|
47 | static PyObject *dirstate_item_new(PyTypeObject *subtype, PyObject *args, | |
48 | PyObject *kwds) |
|
48 | PyObject *kwds) | |
49 | { |
|
49 | { | |
50 | /* We do all the initialization here and not a tp_init function because |
|
50 | /* We do all the initialization here and not a tp_init function because | |
51 | * dirstate_item is immutable. */ |
|
51 | * dirstate_item is immutable. */ | |
52 | dirstateItemObject *t; |
|
52 | dirstateItemObject *t; | |
53 | int wc_tracked; |
|
53 | int wc_tracked; | |
54 | int p1_tracked; |
|
54 | int p1_tracked; | |
55 | int p2_info; |
|
55 | int p2_info; | |
56 | int has_meaningful_data; |
|
56 | int has_meaningful_data; | |
57 | int has_meaningful_mtime; |
|
57 | int has_meaningful_mtime; | |
58 | int mode; |
|
58 | int mode; | |
59 | int size; |
|
59 | int size; | |
60 | int mtime; |
|
60 | int mtime; | |
61 | PyObject *parentfiledata; |
|
61 | PyObject *parentfiledata; | |
62 | static char *keywords_name[] = { |
|
62 | static char *keywords_name[] = { | |
63 | "wc_tracked", |
|
63 | "wc_tracked", | |
64 | "p1_tracked", |
|
64 | "p1_tracked", | |
65 | "p2_info", |
|
65 | "p2_info", | |
66 | "has_meaningful_data", |
|
66 | "has_meaningful_data", | |
67 | "has_meaningful_mtime", |
|
67 | "has_meaningful_mtime", | |
68 | "parentfiledata", |
|
68 | "parentfiledata", | |
69 | NULL, |
|
69 | NULL, | |
70 | }; |
|
70 | }; | |
71 | wc_tracked = 0; |
|
71 | wc_tracked = 0; | |
72 | p1_tracked = 0; |
|
72 | p1_tracked = 0; | |
73 | p2_info = 0; |
|
73 | p2_info = 0; | |
74 | has_meaningful_mtime = 1; |
|
74 | has_meaningful_mtime = 1; | |
75 | has_meaningful_data = 1; |
|
75 | has_meaningful_data = 1; | |
76 | parentfiledata = Py_None; |
|
76 | parentfiledata = Py_None; | |
77 | if (!PyArg_ParseTupleAndKeywords( |
|
77 | if (!PyArg_ParseTupleAndKeywords( | |
78 | args, kwds, "|iiiiiO", keywords_name, &wc_tracked, &p1_tracked, |
|
78 | args, kwds, "|iiiiiO", keywords_name, &wc_tracked, &p1_tracked, | |
79 | &p2_info, &has_meaningful_data, &has_meaningful_mtime, |
|
79 | &p2_info, &has_meaningful_data, &has_meaningful_mtime, | |
80 | &parentfiledata)) { |
|
80 | &parentfiledata)) { | |
81 | return NULL; |
|
81 | return NULL; | |
82 | } |
|
82 | } | |
83 | t = (dirstateItemObject *)subtype->tp_alloc(subtype, 1); |
|
83 | t = (dirstateItemObject *)subtype->tp_alloc(subtype, 1); | |
84 | if (!t) { |
|
84 | if (!t) { | |
85 | return NULL; |
|
85 | return NULL; | |
86 | } |
|
86 | } | |
87 |
|
87 | |||
88 | t->flags = 0; |
|
88 | t->flags = 0; | |
89 | if (wc_tracked) { |
|
89 | if (wc_tracked) { | |
90 | t->flags |= dirstate_flag_wc_tracked; |
|
90 | t->flags |= dirstate_flag_wc_tracked; | |
91 | } |
|
91 | } | |
92 | if (p1_tracked) { |
|
92 | if (p1_tracked) { | |
93 | t->flags |= dirstate_flag_p1_tracked; |
|
93 | t->flags |= dirstate_flag_p1_tracked; | |
94 | } |
|
94 | } | |
95 | if (p2_info) { |
|
95 | if (p2_info) { | |
96 | t->flags |= dirstate_flag_p2_info; |
|
96 | t->flags |= dirstate_flag_p2_info; | |
97 | } |
|
97 | } | |
98 |
|
98 | |||
99 | if (parentfiledata != Py_None) { |
|
99 | if (parentfiledata != Py_None) { | |
100 | if (!PyTuple_CheckExact(parentfiledata)) { |
|
100 | if (!PyTuple_CheckExact(parentfiledata)) { | |
101 | PyErr_SetString( |
|
101 | PyErr_SetString( | |
102 | PyExc_TypeError, |
|
102 | PyExc_TypeError, | |
103 | "parentfiledata should be a Tuple or None"); |
|
103 | "parentfiledata should be a Tuple or None"); | |
104 | return NULL; |
|
104 | return NULL; | |
105 | } |
|
105 | } | |
106 | mode = (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 0)); |
|
106 | mode = (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 0)); | |
107 | size = (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 1)); |
|
107 | size = (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 1)); | |
108 | mtime = (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 2)); |
|
108 | mtime = (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 2)); | |
109 | } else { |
|
109 | } else { | |
110 | has_meaningful_data = 0; |
|
110 | has_meaningful_data = 0; | |
111 | has_meaningful_mtime = 0; |
|
111 | has_meaningful_mtime = 0; | |
112 | } |
|
112 | } | |
113 | if (has_meaningful_data) { |
|
113 | if (has_meaningful_data) { | |
114 | t->flags |= dirstate_flag_has_meaningful_data; |
|
114 | t->flags |= dirstate_flag_has_meaningful_data; | |
115 | t->mode = mode; |
|
115 | t->mode = mode; | |
116 | t->size = size; |
|
116 | t->size = size; | |
117 | } else { |
|
117 | } else { | |
118 | t->mode = 0; |
|
118 | t->mode = 0; | |
119 | t->size = 0; |
|
119 | t->size = 0; | |
120 | } |
|
120 | } | |
121 | if (has_meaningful_mtime) { |
|
121 | if (has_meaningful_mtime) { | |
122 |
t->flags |= dirstate_flag_has_ |
|
122 | t->flags |= dirstate_flag_has_file_mtime; | |
123 | t->mtime = mtime; |
|
123 | t->mtime = mtime; | |
124 | } else { |
|
124 | } else { | |
125 | t->mtime = 0; |
|
125 | t->mtime = 0; | |
126 | } |
|
126 | } | |
127 | return (PyObject *)t; |
|
127 | return (PyObject *)t; | |
128 | } |
|
128 | } | |
129 |
|
129 | |||
130 | static void dirstate_item_dealloc(PyObject *o) |
|
130 | static void dirstate_item_dealloc(PyObject *o) | |
131 | { |
|
131 | { | |
132 | PyObject_Del(o); |
|
132 | PyObject_Del(o); | |
133 | } |
|
133 | } | |
134 |
|
134 | |||
135 | static inline bool dirstate_item_c_tracked(dirstateItemObject *self) |
|
135 | static inline bool dirstate_item_c_tracked(dirstateItemObject *self) | |
136 | { |
|
136 | { | |
137 | return (self->flags & dirstate_flag_wc_tracked); |
|
137 | return (self->flags & dirstate_flag_wc_tracked); | |
138 | } |
|
138 | } | |
139 |
|
139 | |||
140 | static inline bool dirstate_item_c_any_tracked(dirstateItemObject *self) |
|
140 | static inline bool dirstate_item_c_any_tracked(dirstateItemObject *self) | |
141 | { |
|
141 | { | |
142 | const unsigned char mask = dirstate_flag_wc_tracked | |
|
142 | const unsigned char mask = dirstate_flag_wc_tracked | | |
143 | dirstate_flag_p1_tracked | |
|
143 | dirstate_flag_p1_tracked | | |
144 | dirstate_flag_p2_info; |
|
144 | dirstate_flag_p2_info; | |
145 | return (self->flags & mask); |
|
145 | return (self->flags & mask); | |
146 | } |
|
146 | } | |
147 |
|
147 | |||
148 | static inline bool dirstate_item_c_added(dirstateItemObject *self) |
|
148 | static inline bool dirstate_item_c_added(dirstateItemObject *self) | |
149 | { |
|
149 | { | |
150 | const unsigned char mask = |
|
150 | const unsigned char mask = | |
151 | (dirstate_flag_wc_tracked | dirstate_flag_p1_tracked | |
|
151 | (dirstate_flag_wc_tracked | dirstate_flag_p1_tracked | | |
152 | dirstate_flag_p2_info); |
|
152 | dirstate_flag_p2_info); | |
153 | const unsigned char target = dirstate_flag_wc_tracked; |
|
153 | const unsigned char target = dirstate_flag_wc_tracked; | |
154 | return (self->flags & mask) == target; |
|
154 | return (self->flags & mask) == target; | |
155 | } |
|
155 | } | |
156 |
|
156 | |||
157 | static inline bool dirstate_item_c_removed(dirstateItemObject *self) |
|
157 | static inline bool dirstate_item_c_removed(dirstateItemObject *self) | |
158 | { |
|
158 | { | |
159 | if (self->flags & dirstate_flag_wc_tracked) { |
|
159 | if (self->flags & dirstate_flag_wc_tracked) { | |
160 | return false; |
|
160 | return false; | |
161 | } |
|
161 | } | |
162 | return (self->flags & |
|
162 | return (self->flags & | |
163 | (dirstate_flag_p1_tracked | dirstate_flag_p2_info)); |
|
163 | (dirstate_flag_p1_tracked | dirstate_flag_p2_info)); | |
164 | } |
|
164 | } | |
165 |
|
165 | |||
166 | static inline bool dirstate_item_c_merged(dirstateItemObject *self) |
|
166 | static inline bool dirstate_item_c_merged(dirstateItemObject *self) | |
167 | { |
|
167 | { | |
168 | return ((self->flags & dirstate_flag_wc_tracked) && |
|
168 | return ((self->flags & dirstate_flag_wc_tracked) && | |
169 | (self->flags & dirstate_flag_p1_tracked) && |
|
169 | (self->flags & dirstate_flag_p1_tracked) && | |
170 | (self->flags & dirstate_flag_p2_info)); |
|
170 | (self->flags & dirstate_flag_p2_info)); | |
171 | } |
|
171 | } | |
172 |
|
172 | |||
173 | static inline bool dirstate_item_c_from_p2(dirstateItemObject *self) |
|
173 | static inline bool dirstate_item_c_from_p2(dirstateItemObject *self) | |
174 | { |
|
174 | { | |
175 | return ((self->flags & dirstate_flag_wc_tracked) && |
|
175 | return ((self->flags & dirstate_flag_wc_tracked) && | |
176 | !(self->flags & dirstate_flag_p1_tracked) && |
|
176 | !(self->flags & dirstate_flag_p1_tracked) && | |
177 | (self->flags & dirstate_flag_p2_info)); |
|
177 | (self->flags & dirstate_flag_p2_info)); | |
178 | } |
|
178 | } | |
179 |
|
179 | |||
180 | static inline char dirstate_item_c_v1_state(dirstateItemObject *self) |
|
180 | static inline char dirstate_item_c_v1_state(dirstateItemObject *self) | |
181 | { |
|
181 | { | |
182 | if (dirstate_item_c_removed(self)) { |
|
182 | if (dirstate_item_c_removed(self)) { | |
183 | return 'r'; |
|
183 | return 'r'; | |
184 | } else if (dirstate_item_c_merged(self)) { |
|
184 | } else if (dirstate_item_c_merged(self)) { | |
185 | return 'm'; |
|
185 | return 'm'; | |
186 | } else if (dirstate_item_c_added(self)) { |
|
186 | } else if (dirstate_item_c_added(self)) { | |
187 | return 'a'; |
|
187 | return 'a'; | |
188 | } else { |
|
188 | } else { | |
189 | return 'n'; |
|
189 | return 'n'; | |
190 | } |
|
190 | } | |
191 | } |
|
191 | } | |
192 |
|
192 | |||
193 | static inline int dirstate_item_c_v1_mode(dirstateItemObject *self) |
|
193 | static inline int dirstate_item_c_v1_mode(dirstateItemObject *self) | |
194 | { |
|
194 | { | |
195 | if (self->flags & dirstate_flag_has_meaningful_data) { |
|
195 | if (self->flags & dirstate_flag_has_meaningful_data) { | |
196 | return self->mode; |
|
196 | return self->mode; | |
197 | } else { |
|
197 | } else { | |
198 | return 0; |
|
198 | return 0; | |
199 | } |
|
199 | } | |
200 | } |
|
200 | } | |
201 |
|
201 | |||
202 | static inline int dirstate_item_c_v1_size(dirstateItemObject *self) |
|
202 | static inline int dirstate_item_c_v1_size(dirstateItemObject *self) | |
203 | { |
|
203 | { | |
204 | if (!(self->flags & dirstate_flag_wc_tracked) && |
|
204 | if (!(self->flags & dirstate_flag_wc_tracked) && | |
205 | (self->flags & dirstate_flag_p2_info)) { |
|
205 | (self->flags & dirstate_flag_p2_info)) { | |
206 | if (self->flags & dirstate_flag_p1_tracked) { |
|
206 | if (self->flags & dirstate_flag_p1_tracked) { | |
207 | return dirstate_v1_nonnormal; |
|
207 | return dirstate_v1_nonnormal; | |
208 | } else { |
|
208 | } else { | |
209 | return dirstate_v1_from_p2; |
|
209 | return dirstate_v1_from_p2; | |
210 | } |
|
210 | } | |
211 | } else if (dirstate_item_c_removed(self)) { |
|
211 | } else if (dirstate_item_c_removed(self)) { | |
212 | return 0; |
|
212 | return 0; | |
213 | } else if (self->flags & dirstate_flag_p2_info) { |
|
213 | } else if (self->flags & dirstate_flag_p2_info) { | |
214 | return dirstate_v1_from_p2; |
|
214 | return dirstate_v1_from_p2; | |
215 | } else if (dirstate_item_c_added(self)) { |
|
215 | } else if (dirstate_item_c_added(self)) { | |
216 | return dirstate_v1_nonnormal; |
|
216 | return dirstate_v1_nonnormal; | |
217 | } else if (self->flags & dirstate_flag_has_meaningful_data) { |
|
217 | } else if (self->flags & dirstate_flag_has_meaningful_data) { | |
218 | return self->size; |
|
218 | return self->size; | |
219 | } else { |
|
219 | } else { | |
220 | return dirstate_v1_nonnormal; |
|
220 | return dirstate_v1_nonnormal; | |
221 | } |
|
221 | } | |
222 | } |
|
222 | } | |
223 |
|
223 | |||
224 | static inline int dirstate_item_c_v1_mtime(dirstateItemObject *self) |
|
224 | static inline int dirstate_item_c_v1_mtime(dirstateItemObject *self) | |
225 | { |
|
225 | { | |
226 | if (dirstate_item_c_removed(self)) { |
|
226 | if (dirstate_item_c_removed(self)) { | |
227 | return 0; |
|
227 | return 0; | |
228 |
} else if (!(self->flags & dirstate_flag_has_ |
|
228 | } else if (!(self->flags & dirstate_flag_has_file_mtime) || | |
229 | !(self->flags & dirstate_flag_p1_tracked) || |
|
229 | !(self->flags & dirstate_flag_p1_tracked) || | |
230 | !(self->flags & dirstate_flag_wc_tracked) || |
|
230 | !(self->flags & dirstate_flag_wc_tracked) || | |
231 | (self->flags & dirstate_flag_p2_info)) { |
|
231 | (self->flags & dirstate_flag_p2_info)) { | |
232 | return ambiguous_time; |
|
232 | return ambiguous_time; | |
233 | } else { |
|
233 | } else { | |
234 | return self->mtime; |
|
234 | return self->mtime; | |
235 | } |
|
235 | } | |
236 | } |
|
236 | } | |
237 |
|
237 | |||
238 | static PyObject *dirstate_item_v2_data(dirstateItemObject *self) |
|
238 | static PyObject *dirstate_item_v2_data(dirstateItemObject *self) | |
239 | { |
|
239 | { | |
240 | unsigned char flags = self->flags; |
|
240 | unsigned char flags = self->flags; | |
241 | int mode = dirstate_item_c_v1_mode(self); |
|
241 | int mode = dirstate_item_c_v1_mode(self); | |
242 | if ((mode & S_IXUSR) != 0) { |
|
242 | if ((mode & S_IXUSR) != 0) { | |
243 | flags |= dirstate_flag_mode_exec_perm; |
|
243 | flags |= dirstate_flag_mode_exec_perm; | |
244 | } else { |
|
244 | } else { | |
245 | flags &= ~dirstate_flag_mode_exec_perm; |
|
245 | flags &= ~dirstate_flag_mode_exec_perm; | |
246 | } |
|
246 | } | |
247 | if (S_ISLNK(mode)) { |
|
247 | if (S_ISLNK(mode)) { | |
248 | flags |= dirstate_flag_mode_is_symlink; |
|
248 | flags |= dirstate_flag_mode_is_symlink; | |
249 | } else { |
|
249 | } else { | |
250 | flags &= ~dirstate_flag_mode_is_symlink; |
|
250 | flags &= ~dirstate_flag_mode_is_symlink; | |
251 | } |
|
251 | } | |
252 | return Py_BuildValue("Bii", flags, self->size, self->mtime); |
|
252 | return Py_BuildValue("Bii", flags, self->size, self->mtime); | |
253 | }; |
|
253 | }; | |
254 |
|
254 | |||
255 | static PyObject *dirstate_item_v1_state(dirstateItemObject *self) |
|
255 | static PyObject *dirstate_item_v1_state(dirstateItemObject *self) | |
256 | { |
|
256 | { | |
257 | char state = dirstate_item_c_v1_state(self); |
|
257 | char state = dirstate_item_c_v1_state(self); | |
258 | return PyBytes_FromStringAndSize(&state, 1); |
|
258 | return PyBytes_FromStringAndSize(&state, 1); | |
259 | }; |
|
259 | }; | |
260 |
|
260 | |||
261 | static PyObject *dirstate_item_v1_mode(dirstateItemObject *self) |
|
261 | static PyObject *dirstate_item_v1_mode(dirstateItemObject *self) | |
262 | { |
|
262 | { | |
263 | return PyInt_FromLong(dirstate_item_c_v1_mode(self)); |
|
263 | return PyInt_FromLong(dirstate_item_c_v1_mode(self)); | |
264 | }; |
|
264 | }; | |
265 |
|
265 | |||
266 | static PyObject *dirstate_item_v1_size(dirstateItemObject *self) |
|
266 | static PyObject *dirstate_item_v1_size(dirstateItemObject *self) | |
267 | { |
|
267 | { | |
268 | return PyInt_FromLong(dirstate_item_c_v1_size(self)); |
|
268 | return PyInt_FromLong(dirstate_item_c_v1_size(self)); | |
269 | }; |
|
269 | }; | |
270 |
|
270 | |||
271 | static PyObject *dirstate_item_v1_mtime(dirstateItemObject *self) |
|
271 | static PyObject *dirstate_item_v1_mtime(dirstateItemObject *self) | |
272 | { |
|
272 | { | |
273 | return PyInt_FromLong(dirstate_item_c_v1_mtime(self)); |
|
273 | return PyInt_FromLong(dirstate_item_c_v1_mtime(self)); | |
274 | }; |
|
274 | }; | |
275 |
|
275 | |||
276 | static PyObject *dirstate_item_need_delay(dirstateItemObject *self, |
|
276 | static PyObject *dirstate_item_need_delay(dirstateItemObject *self, | |
277 | PyObject *value) |
|
277 | PyObject *value) | |
278 | { |
|
278 | { | |
279 | long now; |
|
279 | long now; | |
280 | if (!pylong_to_long(value, &now)) { |
|
280 | if (!pylong_to_long(value, &now)) { | |
281 | return NULL; |
|
281 | return NULL; | |
282 | } |
|
282 | } | |
283 | if (dirstate_item_c_v1_state(self) == 'n' && |
|
283 | if (dirstate_item_c_v1_state(self) == 'n' && | |
284 | dirstate_item_c_v1_mtime(self) == now) { |
|
284 | dirstate_item_c_v1_mtime(self) == now) { | |
285 | Py_RETURN_TRUE; |
|
285 | Py_RETURN_TRUE; | |
286 | } else { |
|
286 | } else { | |
287 | Py_RETURN_FALSE; |
|
287 | Py_RETURN_FALSE; | |
288 | } |
|
288 | } | |
289 | }; |
|
289 | }; | |
290 |
|
290 | |||
291 | /* This will never change since it's bound to V1 |
|
291 | /* This will never change since it's bound to V1 | |
292 | */ |
|
292 | */ | |
293 | static inline dirstateItemObject * |
|
293 | static inline dirstateItemObject * | |
294 | dirstate_item_from_v1_data(char state, int mode, int size, int mtime) |
|
294 | dirstate_item_from_v1_data(char state, int mode, int size, int mtime) | |
295 | { |
|
295 | { | |
296 | dirstateItemObject *t = |
|
296 | dirstateItemObject *t = | |
297 | PyObject_New(dirstateItemObject, &dirstateItemType); |
|
297 | PyObject_New(dirstateItemObject, &dirstateItemType); | |
298 | if (!t) { |
|
298 | if (!t) { | |
299 | return NULL; |
|
299 | return NULL; | |
300 | } |
|
300 | } | |
301 | t->flags = 0; |
|
301 | t->flags = 0; | |
302 | t->mode = 0; |
|
302 | t->mode = 0; | |
303 | t->size = 0; |
|
303 | t->size = 0; | |
304 | t->mtime = 0; |
|
304 | t->mtime = 0; | |
305 |
|
305 | |||
306 | if (state == 'm') { |
|
306 | if (state == 'm') { | |
307 | t->flags = (dirstate_flag_wc_tracked | |
|
307 | t->flags = (dirstate_flag_wc_tracked | | |
308 | dirstate_flag_p1_tracked | dirstate_flag_p2_info); |
|
308 | dirstate_flag_p1_tracked | dirstate_flag_p2_info); | |
309 | } else if (state == 'a') { |
|
309 | } else if (state == 'a') { | |
310 | t->flags = dirstate_flag_wc_tracked; |
|
310 | t->flags = dirstate_flag_wc_tracked; | |
311 | } else if (state == 'r') { |
|
311 | } else if (state == 'r') { | |
312 | if (size == dirstate_v1_nonnormal) { |
|
312 | if (size == dirstate_v1_nonnormal) { | |
313 | t->flags = |
|
313 | t->flags = | |
314 | dirstate_flag_p1_tracked | dirstate_flag_p2_info; |
|
314 | dirstate_flag_p1_tracked | dirstate_flag_p2_info; | |
315 | } else if (size == dirstate_v1_from_p2) { |
|
315 | } else if (size == dirstate_v1_from_p2) { | |
316 | t->flags = dirstate_flag_p2_info; |
|
316 | t->flags = dirstate_flag_p2_info; | |
317 | } else { |
|
317 | } else { | |
318 | t->flags = dirstate_flag_p1_tracked; |
|
318 | t->flags = dirstate_flag_p1_tracked; | |
319 | } |
|
319 | } | |
320 | } else if (state == 'n') { |
|
320 | } else if (state == 'n') { | |
321 | if (size == dirstate_v1_from_p2) { |
|
321 | if (size == dirstate_v1_from_p2) { | |
322 | t->flags = |
|
322 | t->flags = | |
323 | dirstate_flag_wc_tracked | dirstate_flag_p2_info; |
|
323 | dirstate_flag_wc_tracked | dirstate_flag_p2_info; | |
324 | } else if (size == dirstate_v1_nonnormal) { |
|
324 | } else if (size == dirstate_v1_nonnormal) { | |
325 | t->flags = |
|
325 | t->flags = | |
326 | dirstate_flag_wc_tracked | dirstate_flag_p1_tracked; |
|
326 | dirstate_flag_wc_tracked | dirstate_flag_p1_tracked; | |
327 | } else if (mtime == ambiguous_time) { |
|
327 | } else if (mtime == ambiguous_time) { | |
328 | t->flags = (dirstate_flag_wc_tracked | |
|
328 | t->flags = (dirstate_flag_wc_tracked | | |
329 | dirstate_flag_p1_tracked | |
|
329 | dirstate_flag_p1_tracked | | |
330 | dirstate_flag_has_meaningful_data); |
|
330 | dirstate_flag_has_meaningful_data); | |
331 | t->mode = mode; |
|
331 | t->mode = mode; | |
332 | t->size = size; |
|
332 | t->size = size; | |
333 | } else { |
|
333 | } else { | |
334 | t->flags = (dirstate_flag_wc_tracked | |
|
334 | t->flags = (dirstate_flag_wc_tracked | | |
335 | dirstate_flag_p1_tracked | |
|
335 | dirstate_flag_p1_tracked | | |
336 | dirstate_flag_has_meaningful_data | |
|
336 | dirstate_flag_has_meaningful_data | | |
337 |
dirstate_flag_has_ |
|
337 | dirstate_flag_has_file_mtime); | |
338 | t->mode = mode; |
|
338 | t->mode = mode; | |
339 | t->size = size; |
|
339 | t->size = size; | |
340 | t->mtime = mtime; |
|
340 | t->mtime = mtime; | |
341 | } |
|
341 | } | |
342 | } else { |
|
342 | } else { | |
343 | PyErr_Format(PyExc_RuntimeError, |
|
343 | PyErr_Format(PyExc_RuntimeError, | |
344 | "unknown state: `%c` (%d, %d, %d)", state, mode, |
|
344 | "unknown state: `%c` (%d, %d, %d)", state, mode, | |
345 | size, mtime, NULL); |
|
345 | size, mtime, NULL); | |
346 | Py_DECREF(t); |
|
346 | Py_DECREF(t); | |
347 | return NULL; |
|
347 | return NULL; | |
348 | } |
|
348 | } | |
349 |
|
349 | |||
350 | return t; |
|
350 | return t; | |
351 | } |
|
351 | } | |
352 |
|
352 | |||
353 | /* This will never change since it's bound to V1, unlike `dirstate_item_new` */ |
|
353 | /* This will never change since it's bound to V1, unlike `dirstate_item_new` */ | |
354 | static PyObject *dirstate_item_from_v1_meth(PyTypeObject *subtype, |
|
354 | static PyObject *dirstate_item_from_v1_meth(PyTypeObject *subtype, | |
355 | PyObject *args) |
|
355 | PyObject *args) | |
356 | { |
|
356 | { | |
357 | /* We do all the initialization here and not a tp_init function because |
|
357 | /* We do all the initialization here and not a tp_init function because | |
358 | * dirstate_item is immutable. */ |
|
358 | * dirstate_item is immutable. */ | |
359 | char state; |
|
359 | char state; | |
360 | int size, mode, mtime; |
|
360 | int size, mode, mtime; | |
361 | if (!PyArg_ParseTuple(args, "ciii", &state, &mode, &size, &mtime)) { |
|
361 | if (!PyArg_ParseTuple(args, "ciii", &state, &mode, &size, &mtime)) { | |
362 | return NULL; |
|
362 | return NULL; | |
363 | } |
|
363 | } | |
364 | return (PyObject *)dirstate_item_from_v1_data(state, mode, size, mtime); |
|
364 | return (PyObject *)dirstate_item_from_v1_data(state, mode, size, mtime); | |
365 | }; |
|
365 | }; | |
366 |
|
366 | |||
367 | static PyObject *dirstate_item_from_v2_meth(PyTypeObject *subtype, |
|
367 | static PyObject *dirstate_item_from_v2_meth(PyTypeObject *subtype, | |
368 | PyObject *args) |
|
368 | PyObject *args) | |
369 | { |
|
369 | { | |
370 | dirstateItemObject *t = |
|
370 | dirstateItemObject *t = | |
371 | PyObject_New(dirstateItemObject, &dirstateItemType); |
|
371 | PyObject_New(dirstateItemObject, &dirstateItemType); | |
372 | if (!t) { |
|
372 | if (!t) { | |
373 | return NULL; |
|
373 | return NULL; | |
374 | } |
|
374 | } | |
375 | if (!PyArg_ParseTuple(args, "bii", &t->flags, &t->size, &t->mtime)) { |
|
375 | if (!PyArg_ParseTuple(args, "bii", &t->flags, &t->size, &t->mtime)) { | |
376 | return NULL; |
|
376 | return NULL; | |
377 | } |
|
377 | } | |
378 | t->mode = 0; |
|
378 | t->mode = 0; | |
379 | if (t->flags & dirstate_flag_has_meaningful_data) { |
|
379 | if (t->flags & dirstate_flag_has_meaningful_data) { | |
380 | if (t->flags & dirstate_flag_mode_exec_perm) { |
|
380 | if (t->flags & dirstate_flag_mode_exec_perm) { | |
381 | t->mode = 0755; |
|
381 | t->mode = 0755; | |
382 | } else { |
|
382 | } else { | |
383 | t->mode = 0644; |
|
383 | t->mode = 0644; | |
384 | } |
|
384 | } | |
385 | if (t->flags & dirstate_flag_mode_is_symlink) { |
|
385 | if (t->flags & dirstate_flag_mode_is_symlink) { | |
386 | t->mode |= S_IFLNK; |
|
386 | t->mode |= S_IFLNK; | |
387 | } else { |
|
387 | } else { | |
388 | t->mode |= S_IFREG; |
|
388 | t->mode |= S_IFREG; | |
389 | } |
|
389 | } | |
390 | } |
|
390 | } | |
391 | return (PyObject *)t; |
|
391 | return (PyObject *)t; | |
392 | }; |
|
392 | }; | |
393 |
|
393 | |||
394 | /* This means the next status call will have to actually check its content |
|
394 | /* This means the next status call will have to actually check its content | |
395 | to make sure it is correct. */ |
|
395 | to make sure it is correct. */ | |
396 | static PyObject *dirstate_item_set_possibly_dirty(dirstateItemObject *self) |
|
396 | static PyObject *dirstate_item_set_possibly_dirty(dirstateItemObject *self) | |
397 | { |
|
397 | { | |
398 |
self->flags &= ~dirstate_flag_has_ |
|
398 | self->flags &= ~dirstate_flag_has_file_mtime; | |
399 | Py_RETURN_NONE; |
|
399 | Py_RETURN_NONE; | |
400 | } |
|
400 | } | |
401 |
|
401 | |||
402 | /* See docstring of the python implementation for details */ |
|
402 | /* See docstring of the python implementation for details */ | |
403 | static PyObject *dirstate_item_set_clean(dirstateItemObject *self, |
|
403 | static PyObject *dirstate_item_set_clean(dirstateItemObject *self, | |
404 | PyObject *args) |
|
404 | PyObject *args) | |
405 | { |
|
405 | { | |
406 | int size, mode, mtime; |
|
406 | int size, mode, mtime; | |
407 | if (!PyArg_ParseTuple(args, "iii", &mode, &size, &mtime)) { |
|
407 | if (!PyArg_ParseTuple(args, "iii", &mode, &size, &mtime)) { | |
408 | return NULL; |
|
408 | return NULL; | |
409 | } |
|
409 | } | |
410 | self->flags = dirstate_flag_wc_tracked | dirstate_flag_p1_tracked | |
|
410 | self->flags = dirstate_flag_wc_tracked | dirstate_flag_p1_tracked | | |
411 | dirstate_flag_has_meaningful_data | |
|
411 | dirstate_flag_has_meaningful_data | | |
412 |
dirstate_flag_has_ |
|
412 | dirstate_flag_has_file_mtime; | |
413 | self->mode = mode; |
|
413 | self->mode = mode; | |
414 | self->size = size; |
|
414 | self->size = size; | |
415 | self->mtime = mtime; |
|
415 | self->mtime = mtime; | |
416 | Py_RETURN_NONE; |
|
416 | Py_RETURN_NONE; | |
417 | } |
|
417 | } | |
418 |
|
418 | |||
419 | static PyObject *dirstate_item_set_tracked(dirstateItemObject *self) |
|
419 | static PyObject *dirstate_item_set_tracked(dirstateItemObject *self) | |
420 | { |
|
420 | { | |
421 | self->flags |= dirstate_flag_wc_tracked; |
|
421 | self->flags |= dirstate_flag_wc_tracked; | |
422 |
self->flags &= ~dirstate_flag_has_ |
|
422 | self->flags &= ~dirstate_flag_has_file_mtime; | |
423 | Py_RETURN_NONE; |
|
423 | Py_RETURN_NONE; | |
424 | } |
|
424 | } | |
425 |
|
425 | |||
426 | static PyObject *dirstate_item_set_untracked(dirstateItemObject *self) |
|
426 | static PyObject *dirstate_item_set_untracked(dirstateItemObject *self) | |
427 | { |
|
427 | { | |
428 | self->flags &= ~dirstate_flag_wc_tracked; |
|
428 | self->flags &= ~dirstate_flag_wc_tracked; | |
429 | self->mode = 0; |
|
429 | self->mode = 0; | |
430 | self->mtime = 0; |
|
430 | self->mtime = 0; | |
431 | self->size = 0; |
|
431 | self->size = 0; | |
432 | Py_RETURN_NONE; |
|
432 | Py_RETURN_NONE; | |
433 | } |
|
433 | } | |
434 |
|
434 | |||
435 | static PyObject *dirstate_item_drop_merge_data(dirstateItemObject *self) |
|
435 | static PyObject *dirstate_item_drop_merge_data(dirstateItemObject *self) | |
436 | { |
|
436 | { | |
437 | if (self->flags & dirstate_flag_p2_info) { |
|
437 | if (self->flags & dirstate_flag_p2_info) { | |
438 | self->flags &= ~(dirstate_flag_p2_info | |
|
438 | self->flags &= ~(dirstate_flag_p2_info | | |
439 | dirstate_flag_has_meaningful_data | |
|
439 | dirstate_flag_has_meaningful_data | | |
440 |
dirstate_flag_has_ |
|
440 | dirstate_flag_has_file_mtime); | |
441 | self->mode = 0; |
|
441 | self->mode = 0; | |
442 | self->mtime = 0; |
|
442 | self->mtime = 0; | |
443 | self->size = 0; |
|
443 | self->size = 0; | |
444 | } |
|
444 | } | |
445 | Py_RETURN_NONE; |
|
445 | Py_RETURN_NONE; | |
446 | } |
|
446 | } | |
447 | static PyMethodDef dirstate_item_methods[] = { |
|
447 | static PyMethodDef dirstate_item_methods[] = { | |
448 | {"v2_data", (PyCFunction)dirstate_item_v2_data, METH_NOARGS, |
|
448 | {"v2_data", (PyCFunction)dirstate_item_v2_data, METH_NOARGS, | |
449 | "return data suitable for v2 serialization"}, |
|
449 | "return data suitable for v2 serialization"}, | |
450 | {"v1_state", (PyCFunction)dirstate_item_v1_state, METH_NOARGS, |
|
450 | {"v1_state", (PyCFunction)dirstate_item_v1_state, METH_NOARGS, | |
451 | "return a \"state\" suitable for v1 serialization"}, |
|
451 | "return a \"state\" suitable for v1 serialization"}, | |
452 | {"v1_mode", (PyCFunction)dirstate_item_v1_mode, METH_NOARGS, |
|
452 | {"v1_mode", (PyCFunction)dirstate_item_v1_mode, METH_NOARGS, | |
453 | "return a \"mode\" suitable for v1 serialization"}, |
|
453 | "return a \"mode\" suitable for v1 serialization"}, | |
454 | {"v1_size", (PyCFunction)dirstate_item_v1_size, METH_NOARGS, |
|
454 | {"v1_size", (PyCFunction)dirstate_item_v1_size, METH_NOARGS, | |
455 | "return a \"size\" suitable for v1 serialization"}, |
|
455 | "return a \"size\" suitable for v1 serialization"}, | |
456 | {"v1_mtime", (PyCFunction)dirstate_item_v1_mtime, METH_NOARGS, |
|
456 | {"v1_mtime", (PyCFunction)dirstate_item_v1_mtime, METH_NOARGS, | |
457 | "return a \"mtime\" suitable for v1 serialization"}, |
|
457 | "return a \"mtime\" suitable for v1 serialization"}, | |
458 | {"need_delay", (PyCFunction)dirstate_item_need_delay, METH_O, |
|
458 | {"need_delay", (PyCFunction)dirstate_item_need_delay, METH_O, | |
459 | "True if the stored mtime would be ambiguous with the current time"}, |
|
459 | "True if the stored mtime would be ambiguous with the current time"}, | |
460 | {"from_v1_data", (PyCFunction)dirstate_item_from_v1_meth, |
|
460 | {"from_v1_data", (PyCFunction)dirstate_item_from_v1_meth, | |
461 | METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V1 data"}, |
|
461 | METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V1 data"}, | |
462 | {"from_v2_data", (PyCFunction)dirstate_item_from_v2_meth, |
|
462 | {"from_v2_data", (PyCFunction)dirstate_item_from_v2_meth, | |
463 | METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V2 data"}, |
|
463 | METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V2 data"}, | |
464 | {"set_possibly_dirty", (PyCFunction)dirstate_item_set_possibly_dirty, |
|
464 | {"set_possibly_dirty", (PyCFunction)dirstate_item_set_possibly_dirty, | |
465 | METH_NOARGS, "mark a file as \"possibly dirty\""}, |
|
465 | METH_NOARGS, "mark a file as \"possibly dirty\""}, | |
466 | {"set_clean", (PyCFunction)dirstate_item_set_clean, METH_VARARGS, |
|
466 | {"set_clean", (PyCFunction)dirstate_item_set_clean, METH_VARARGS, | |
467 | "mark a file as \"clean\""}, |
|
467 | "mark a file as \"clean\""}, | |
468 | {"set_tracked", (PyCFunction)dirstate_item_set_tracked, METH_NOARGS, |
|
468 | {"set_tracked", (PyCFunction)dirstate_item_set_tracked, METH_NOARGS, | |
469 | "mark a file as \"tracked\""}, |
|
469 | "mark a file as \"tracked\""}, | |
470 | {"set_untracked", (PyCFunction)dirstate_item_set_untracked, METH_NOARGS, |
|
470 | {"set_untracked", (PyCFunction)dirstate_item_set_untracked, METH_NOARGS, | |
471 | "mark a file as \"untracked\""}, |
|
471 | "mark a file as \"untracked\""}, | |
472 | {"drop_merge_data", (PyCFunction)dirstate_item_drop_merge_data, METH_NOARGS, |
|
472 | {"drop_merge_data", (PyCFunction)dirstate_item_drop_merge_data, METH_NOARGS, | |
473 | "remove all \"merge-only\" from a DirstateItem"}, |
|
473 | "remove all \"merge-only\" from a DirstateItem"}, | |
474 | {NULL} /* Sentinel */ |
|
474 | {NULL} /* Sentinel */ | |
475 | }; |
|
475 | }; | |
476 |
|
476 | |||
477 | static PyObject *dirstate_item_get_mode(dirstateItemObject *self) |
|
477 | static PyObject *dirstate_item_get_mode(dirstateItemObject *self) | |
478 | { |
|
478 | { | |
479 | return PyInt_FromLong(dirstate_item_c_v1_mode(self)); |
|
479 | return PyInt_FromLong(dirstate_item_c_v1_mode(self)); | |
480 | }; |
|
480 | }; | |
481 |
|
481 | |||
482 | static PyObject *dirstate_item_get_size(dirstateItemObject *self) |
|
482 | static PyObject *dirstate_item_get_size(dirstateItemObject *self) | |
483 | { |
|
483 | { | |
484 | return PyInt_FromLong(dirstate_item_c_v1_size(self)); |
|
484 | return PyInt_FromLong(dirstate_item_c_v1_size(self)); | |
485 | }; |
|
485 | }; | |
486 |
|
486 | |||
487 | static PyObject *dirstate_item_get_mtime(dirstateItemObject *self) |
|
487 | static PyObject *dirstate_item_get_mtime(dirstateItemObject *self) | |
488 | { |
|
488 | { | |
489 | return PyInt_FromLong(dirstate_item_c_v1_mtime(self)); |
|
489 | return PyInt_FromLong(dirstate_item_c_v1_mtime(self)); | |
490 | }; |
|
490 | }; | |
491 |
|
491 | |||
492 | static PyObject *dirstate_item_get_state(dirstateItemObject *self) |
|
492 | static PyObject *dirstate_item_get_state(dirstateItemObject *self) | |
493 | { |
|
493 | { | |
494 | char state = dirstate_item_c_v1_state(self); |
|
494 | char state = dirstate_item_c_v1_state(self); | |
495 | return PyBytes_FromStringAndSize(&state, 1); |
|
495 | return PyBytes_FromStringAndSize(&state, 1); | |
496 | }; |
|
496 | }; | |
497 |
|
497 | |||
498 | static PyObject *dirstate_item_get_tracked(dirstateItemObject *self) |
|
498 | static PyObject *dirstate_item_get_tracked(dirstateItemObject *self) | |
499 | { |
|
499 | { | |
500 | if (dirstate_item_c_tracked(self)) { |
|
500 | if (dirstate_item_c_tracked(self)) { | |
501 | Py_RETURN_TRUE; |
|
501 | Py_RETURN_TRUE; | |
502 | } else { |
|
502 | } else { | |
503 | Py_RETURN_FALSE; |
|
503 | Py_RETURN_FALSE; | |
504 | } |
|
504 | } | |
505 | }; |
|
505 | }; | |
506 | static PyObject *dirstate_item_get_p1_tracked(dirstateItemObject *self) |
|
506 | static PyObject *dirstate_item_get_p1_tracked(dirstateItemObject *self) | |
507 | { |
|
507 | { | |
508 | if (self->flags & dirstate_flag_p1_tracked) { |
|
508 | if (self->flags & dirstate_flag_p1_tracked) { | |
509 | Py_RETURN_TRUE; |
|
509 | Py_RETURN_TRUE; | |
510 | } else { |
|
510 | } else { | |
511 | Py_RETURN_FALSE; |
|
511 | Py_RETURN_FALSE; | |
512 | } |
|
512 | } | |
513 | }; |
|
513 | }; | |
514 |
|
514 | |||
515 | static PyObject *dirstate_item_get_added(dirstateItemObject *self) |
|
515 | static PyObject *dirstate_item_get_added(dirstateItemObject *self) | |
516 | { |
|
516 | { | |
517 | if (dirstate_item_c_added(self)) { |
|
517 | if (dirstate_item_c_added(self)) { | |
518 | Py_RETURN_TRUE; |
|
518 | Py_RETURN_TRUE; | |
519 | } else { |
|
519 | } else { | |
520 | Py_RETURN_FALSE; |
|
520 | Py_RETURN_FALSE; | |
521 | } |
|
521 | } | |
522 | }; |
|
522 | }; | |
523 |
|
523 | |||
524 | static PyObject *dirstate_item_get_p2_info(dirstateItemObject *self) |
|
524 | static PyObject *dirstate_item_get_p2_info(dirstateItemObject *self) | |
525 | { |
|
525 | { | |
526 | if (self->flags & dirstate_flag_wc_tracked && |
|
526 | if (self->flags & dirstate_flag_wc_tracked && | |
527 | self->flags & dirstate_flag_p2_info) { |
|
527 | self->flags & dirstate_flag_p2_info) { | |
528 | Py_RETURN_TRUE; |
|
528 | Py_RETURN_TRUE; | |
529 | } else { |
|
529 | } else { | |
530 | Py_RETURN_FALSE; |
|
530 | Py_RETURN_FALSE; | |
531 | } |
|
531 | } | |
532 | }; |
|
532 | }; | |
533 |
|
533 | |||
534 | static PyObject *dirstate_item_get_merged(dirstateItemObject *self) |
|
534 | static PyObject *dirstate_item_get_merged(dirstateItemObject *self) | |
535 | { |
|
535 | { | |
536 | if (dirstate_item_c_merged(self)) { |
|
536 | if (dirstate_item_c_merged(self)) { | |
537 | Py_RETURN_TRUE; |
|
537 | Py_RETURN_TRUE; | |
538 | } else { |
|
538 | } else { | |
539 | Py_RETURN_FALSE; |
|
539 | Py_RETURN_FALSE; | |
540 | } |
|
540 | } | |
541 | }; |
|
541 | }; | |
542 |
|
542 | |||
543 | static PyObject *dirstate_item_get_from_p2(dirstateItemObject *self) |
|
543 | static PyObject *dirstate_item_get_from_p2(dirstateItemObject *self) | |
544 | { |
|
544 | { | |
545 | if (dirstate_item_c_from_p2(self)) { |
|
545 | if (dirstate_item_c_from_p2(self)) { | |
546 | Py_RETURN_TRUE; |
|
546 | Py_RETURN_TRUE; | |
547 | } else { |
|
547 | } else { | |
548 | Py_RETURN_FALSE; |
|
548 | Py_RETURN_FALSE; | |
549 | } |
|
549 | } | |
550 | }; |
|
550 | }; | |
551 |
|
551 | |||
552 | static PyObject *dirstate_item_get_maybe_clean(dirstateItemObject *self) |
|
552 | static PyObject *dirstate_item_get_maybe_clean(dirstateItemObject *self) | |
553 | { |
|
553 | { | |
554 | if (!(self->flags & dirstate_flag_wc_tracked)) { |
|
554 | if (!(self->flags & dirstate_flag_wc_tracked)) { | |
555 | Py_RETURN_FALSE; |
|
555 | Py_RETURN_FALSE; | |
556 | } else if (!(self->flags & dirstate_flag_p1_tracked)) { |
|
556 | } else if (!(self->flags & dirstate_flag_p1_tracked)) { | |
557 | Py_RETURN_FALSE; |
|
557 | Py_RETURN_FALSE; | |
558 | } else if (self->flags & dirstate_flag_p2_info) { |
|
558 | } else if (self->flags & dirstate_flag_p2_info) { | |
559 | Py_RETURN_FALSE; |
|
559 | Py_RETURN_FALSE; | |
560 | } else { |
|
560 | } else { | |
561 | Py_RETURN_TRUE; |
|
561 | Py_RETURN_TRUE; | |
562 | } |
|
562 | } | |
563 | }; |
|
563 | }; | |
564 |
|
564 | |||
565 | static PyObject *dirstate_item_get_any_tracked(dirstateItemObject *self) |
|
565 | static PyObject *dirstate_item_get_any_tracked(dirstateItemObject *self) | |
566 | { |
|
566 | { | |
567 | if (dirstate_item_c_any_tracked(self)) { |
|
567 | if (dirstate_item_c_any_tracked(self)) { | |
568 | Py_RETURN_TRUE; |
|
568 | Py_RETURN_TRUE; | |
569 | } else { |
|
569 | } else { | |
570 | Py_RETURN_FALSE; |
|
570 | Py_RETURN_FALSE; | |
571 | } |
|
571 | } | |
572 | }; |
|
572 | }; | |
573 |
|
573 | |||
574 | static PyObject *dirstate_item_get_removed(dirstateItemObject *self) |
|
574 | static PyObject *dirstate_item_get_removed(dirstateItemObject *self) | |
575 | { |
|
575 | { | |
576 | if (dirstate_item_c_removed(self)) { |
|
576 | if (dirstate_item_c_removed(self)) { | |
577 | Py_RETURN_TRUE; |
|
577 | Py_RETURN_TRUE; | |
578 | } else { |
|
578 | } else { | |
579 | Py_RETURN_FALSE; |
|
579 | Py_RETURN_FALSE; | |
580 | } |
|
580 | } | |
581 | }; |
|
581 | }; | |
582 |
|
582 | |||
583 | static PyGetSetDef dirstate_item_getset[] = { |
|
583 | static PyGetSetDef dirstate_item_getset[] = { | |
584 | {"mode", (getter)dirstate_item_get_mode, NULL, "mode", NULL}, |
|
584 | {"mode", (getter)dirstate_item_get_mode, NULL, "mode", NULL}, | |
585 | {"size", (getter)dirstate_item_get_size, NULL, "size", NULL}, |
|
585 | {"size", (getter)dirstate_item_get_size, NULL, "size", NULL}, | |
586 | {"mtime", (getter)dirstate_item_get_mtime, NULL, "mtime", NULL}, |
|
586 | {"mtime", (getter)dirstate_item_get_mtime, NULL, "mtime", NULL}, | |
587 | {"state", (getter)dirstate_item_get_state, NULL, "state", NULL}, |
|
587 | {"state", (getter)dirstate_item_get_state, NULL, "state", NULL}, | |
588 | {"tracked", (getter)dirstate_item_get_tracked, NULL, "tracked", NULL}, |
|
588 | {"tracked", (getter)dirstate_item_get_tracked, NULL, "tracked", NULL}, | |
589 | {"p1_tracked", (getter)dirstate_item_get_p1_tracked, NULL, "p1_tracked", |
|
589 | {"p1_tracked", (getter)dirstate_item_get_p1_tracked, NULL, "p1_tracked", | |
590 | NULL}, |
|
590 | NULL}, | |
591 | {"added", (getter)dirstate_item_get_added, NULL, "added", NULL}, |
|
591 | {"added", (getter)dirstate_item_get_added, NULL, "added", NULL}, | |
592 | {"p2_info", (getter)dirstate_item_get_p2_info, NULL, "p2_info", NULL}, |
|
592 | {"p2_info", (getter)dirstate_item_get_p2_info, NULL, "p2_info", NULL}, | |
593 | {"merged", (getter)dirstate_item_get_merged, NULL, "merged", NULL}, |
|
593 | {"merged", (getter)dirstate_item_get_merged, NULL, "merged", NULL}, | |
594 | {"from_p2", (getter)dirstate_item_get_from_p2, NULL, "from_p2", NULL}, |
|
594 | {"from_p2", (getter)dirstate_item_get_from_p2, NULL, "from_p2", NULL}, | |
595 | {"maybe_clean", (getter)dirstate_item_get_maybe_clean, NULL, "maybe_clean", |
|
595 | {"maybe_clean", (getter)dirstate_item_get_maybe_clean, NULL, "maybe_clean", | |
596 | NULL}, |
|
596 | NULL}, | |
597 | {"any_tracked", (getter)dirstate_item_get_any_tracked, NULL, "any_tracked", |
|
597 | {"any_tracked", (getter)dirstate_item_get_any_tracked, NULL, "any_tracked", | |
598 | NULL}, |
|
598 | NULL}, | |
599 | {"removed", (getter)dirstate_item_get_removed, NULL, "removed", NULL}, |
|
599 | {"removed", (getter)dirstate_item_get_removed, NULL, "removed", NULL}, | |
600 | {NULL} /* Sentinel */ |
|
600 | {NULL} /* Sentinel */ | |
601 | }; |
|
601 | }; | |
602 |
|
602 | |||
603 | PyTypeObject dirstateItemType = { |
|
603 | PyTypeObject dirstateItemType = { | |
604 | PyVarObject_HEAD_INIT(NULL, 0) /* header */ |
|
604 | PyVarObject_HEAD_INIT(NULL, 0) /* header */ | |
605 | "dirstate_tuple", /* tp_name */ |
|
605 | "dirstate_tuple", /* tp_name */ | |
606 | sizeof(dirstateItemObject), /* tp_basicsize */ |
|
606 | sizeof(dirstateItemObject), /* tp_basicsize */ | |
607 | 0, /* tp_itemsize */ |
|
607 | 0, /* tp_itemsize */ | |
608 | (destructor)dirstate_item_dealloc, /* tp_dealloc */ |
|
608 | (destructor)dirstate_item_dealloc, /* tp_dealloc */ | |
609 | 0, /* tp_print */ |
|
609 | 0, /* tp_print */ | |
610 | 0, /* tp_getattr */ |
|
610 | 0, /* tp_getattr */ | |
611 | 0, /* tp_setattr */ |
|
611 | 0, /* tp_setattr */ | |
612 | 0, /* tp_compare */ |
|
612 | 0, /* tp_compare */ | |
613 | 0, /* tp_repr */ |
|
613 | 0, /* tp_repr */ | |
614 | 0, /* tp_as_number */ |
|
614 | 0, /* tp_as_number */ | |
615 | 0, /* tp_as_sequence */ |
|
615 | 0, /* tp_as_sequence */ | |
616 | 0, /* tp_as_mapping */ |
|
616 | 0, /* tp_as_mapping */ | |
617 | 0, /* tp_hash */ |
|
617 | 0, /* tp_hash */ | |
618 | 0, /* tp_call */ |
|
618 | 0, /* tp_call */ | |
619 | 0, /* tp_str */ |
|
619 | 0, /* tp_str */ | |
620 | 0, /* tp_getattro */ |
|
620 | 0, /* tp_getattro */ | |
621 | 0, /* tp_setattro */ |
|
621 | 0, /* tp_setattro */ | |
622 | 0, /* tp_as_buffer */ |
|
622 | 0, /* tp_as_buffer */ | |
623 | Py_TPFLAGS_DEFAULT, /* tp_flags */ |
|
623 | Py_TPFLAGS_DEFAULT, /* tp_flags */ | |
624 | "dirstate tuple", /* tp_doc */ |
|
624 | "dirstate tuple", /* tp_doc */ | |
625 | 0, /* tp_traverse */ |
|
625 | 0, /* tp_traverse */ | |
626 | 0, /* tp_clear */ |
|
626 | 0, /* tp_clear */ | |
627 | 0, /* tp_richcompare */ |
|
627 | 0, /* tp_richcompare */ | |
628 | 0, /* tp_weaklistoffset */ |
|
628 | 0, /* tp_weaklistoffset */ | |
629 | 0, /* tp_iter */ |
|
629 | 0, /* tp_iter */ | |
630 | 0, /* tp_iternext */ |
|
630 | 0, /* tp_iternext */ | |
631 | dirstate_item_methods, /* tp_methods */ |
|
631 | dirstate_item_methods, /* tp_methods */ | |
632 | 0, /* tp_members */ |
|
632 | 0, /* tp_members */ | |
633 | dirstate_item_getset, /* tp_getset */ |
|
633 | dirstate_item_getset, /* tp_getset */ | |
634 | 0, /* tp_base */ |
|
634 | 0, /* tp_base */ | |
635 | 0, /* tp_dict */ |
|
635 | 0, /* tp_dict */ | |
636 | 0, /* tp_descr_get */ |
|
636 | 0, /* tp_descr_get */ | |
637 | 0, /* tp_descr_set */ |
|
637 | 0, /* tp_descr_set */ | |
638 | 0, /* tp_dictoffset */ |
|
638 | 0, /* tp_dictoffset */ | |
639 | 0, /* tp_init */ |
|
639 | 0, /* tp_init */ | |
640 | 0, /* tp_alloc */ |
|
640 | 0, /* tp_alloc */ | |
641 | dirstate_item_new, /* tp_new */ |
|
641 | dirstate_item_new, /* tp_new */ | |
642 | }; |
|
642 | }; | |
643 |
|
643 | |||
644 | static PyObject *parse_dirstate(PyObject *self, PyObject *args) |
|
644 | static PyObject *parse_dirstate(PyObject *self, PyObject *args) | |
645 | { |
|
645 | { | |
646 | PyObject *dmap, *cmap, *parents = NULL, *ret = NULL; |
|
646 | PyObject *dmap, *cmap, *parents = NULL, *ret = NULL; | |
647 | PyObject *fname = NULL, *cname = NULL, *entry = NULL; |
|
647 | PyObject *fname = NULL, *cname = NULL, *entry = NULL; | |
648 | char state, *cur, *str, *cpos; |
|
648 | char state, *cur, *str, *cpos; | |
649 | int mode, size, mtime; |
|
649 | int mode, size, mtime; | |
650 | unsigned int flen, pos = 40; |
|
650 | unsigned int flen, pos = 40; | |
651 | Py_ssize_t len = 40; |
|
651 | Py_ssize_t len = 40; | |
652 | Py_ssize_t readlen; |
|
652 | Py_ssize_t readlen; | |
653 |
|
653 | |||
654 | if (!PyArg_ParseTuple( |
|
654 | if (!PyArg_ParseTuple( | |
655 | args, PY23("O!O!s#:parse_dirstate", "O!O!y#:parse_dirstate"), |
|
655 | args, PY23("O!O!s#:parse_dirstate", "O!O!y#:parse_dirstate"), | |
656 | &PyDict_Type, &dmap, &PyDict_Type, &cmap, &str, &readlen)) { |
|
656 | &PyDict_Type, &dmap, &PyDict_Type, &cmap, &str, &readlen)) { | |
657 | goto quit; |
|
657 | goto quit; | |
658 | } |
|
658 | } | |
659 |
|
659 | |||
660 | len = readlen; |
|
660 | len = readlen; | |
661 |
|
661 | |||
662 | /* read parents */ |
|
662 | /* read parents */ | |
663 | if (len < 40) { |
|
663 | if (len < 40) { | |
664 | PyErr_SetString(PyExc_ValueError, |
|
664 | PyErr_SetString(PyExc_ValueError, | |
665 | "too little data for parents"); |
|
665 | "too little data for parents"); | |
666 | goto quit; |
|
666 | goto quit; | |
667 | } |
|
667 | } | |
668 |
|
668 | |||
669 | parents = Py_BuildValue(PY23("s#s#", "y#y#"), str, (Py_ssize_t)20, |
|
669 | parents = Py_BuildValue(PY23("s#s#", "y#y#"), str, (Py_ssize_t)20, | |
670 | str + 20, (Py_ssize_t)20); |
|
670 | str + 20, (Py_ssize_t)20); | |
671 | if (!parents) { |
|
671 | if (!parents) { | |
672 | goto quit; |
|
672 | goto quit; | |
673 | } |
|
673 | } | |
674 |
|
674 | |||
675 | /* read filenames */ |
|
675 | /* read filenames */ | |
676 | while (pos >= 40 && pos < len) { |
|
676 | while (pos >= 40 && pos < len) { | |
677 | if (pos + 17 > len) { |
|
677 | if (pos + 17 > len) { | |
678 | PyErr_SetString(PyExc_ValueError, |
|
678 | PyErr_SetString(PyExc_ValueError, | |
679 | "overflow in dirstate"); |
|
679 | "overflow in dirstate"); | |
680 | goto quit; |
|
680 | goto quit; | |
681 | } |
|
681 | } | |
682 | cur = str + pos; |
|
682 | cur = str + pos; | |
683 | /* unpack header */ |
|
683 | /* unpack header */ | |
684 | state = *cur; |
|
684 | state = *cur; | |
685 | mode = getbe32(cur + 1); |
|
685 | mode = getbe32(cur + 1); | |
686 | size = getbe32(cur + 5); |
|
686 | size = getbe32(cur + 5); | |
687 | mtime = getbe32(cur + 9); |
|
687 | mtime = getbe32(cur + 9); | |
688 | flen = getbe32(cur + 13); |
|
688 | flen = getbe32(cur + 13); | |
689 | pos += 17; |
|
689 | pos += 17; | |
690 | cur += 17; |
|
690 | cur += 17; | |
691 | if (flen > len - pos) { |
|
691 | if (flen > len - pos) { | |
692 | PyErr_SetString(PyExc_ValueError, |
|
692 | PyErr_SetString(PyExc_ValueError, | |
693 | "overflow in dirstate"); |
|
693 | "overflow in dirstate"); | |
694 | goto quit; |
|
694 | goto quit; | |
695 | } |
|
695 | } | |
696 |
|
696 | |||
697 | entry = (PyObject *)dirstate_item_from_v1_data(state, mode, |
|
697 | entry = (PyObject *)dirstate_item_from_v1_data(state, mode, | |
698 | size, mtime); |
|
698 | size, mtime); | |
699 | if (!entry) |
|
699 | if (!entry) | |
700 | goto quit; |
|
700 | goto quit; | |
701 | cpos = memchr(cur, 0, flen); |
|
701 | cpos = memchr(cur, 0, flen); | |
702 | if (cpos) { |
|
702 | if (cpos) { | |
703 | fname = PyBytes_FromStringAndSize(cur, cpos - cur); |
|
703 | fname = PyBytes_FromStringAndSize(cur, cpos - cur); | |
704 | cname = PyBytes_FromStringAndSize( |
|
704 | cname = PyBytes_FromStringAndSize( | |
705 | cpos + 1, flen - (cpos - cur) - 1); |
|
705 | cpos + 1, flen - (cpos - cur) - 1); | |
706 | if (!fname || !cname || |
|
706 | if (!fname || !cname || | |
707 | PyDict_SetItem(cmap, fname, cname) == -1 || |
|
707 | PyDict_SetItem(cmap, fname, cname) == -1 || | |
708 | PyDict_SetItem(dmap, fname, entry) == -1) { |
|
708 | PyDict_SetItem(dmap, fname, entry) == -1) { | |
709 | goto quit; |
|
709 | goto quit; | |
710 | } |
|
710 | } | |
711 | Py_DECREF(cname); |
|
711 | Py_DECREF(cname); | |
712 | } else { |
|
712 | } else { | |
713 | fname = PyBytes_FromStringAndSize(cur, flen); |
|
713 | fname = PyBytes_FromStringAndSize(cur, flen); | |
714 | if (!fname || |
|
714 | if (!fname || | |
715 | PyDict_SetItem(dmap, fname, entry) == -1) { |
|
715 | PyDict_SetItem(dmap, fname, entry) == -1) { | |
716 | goto quit; |
|
716 | goto quit; | |
717 | } |
|
717 | } | |
718 | } |
|
718 | } | |
719 | Py_DECREF(fname); |
|
719 | Py_DECREF(fname); | |
720 | Py_DECREF(entry); |
|
720 | Py_DECREF(entry); | |
721 | fname = cname = entry = NULL; |
|
721 | fname = cname = entry = NULL; | |
722 | pos += flen; |
|
722 | pos += flen; | |
723 | } |
|
723 | } | |
724 |
|
724 | |||
725 | ret = parents; |
|
725 | ret = parents; | |
726 | Py_INCREF(ret); |
|
726 | Py_INCREF(ret); | |
727 | quit: |
|
727 | quit: | |
728 | Py_XDECREF(fname); |
|
728 | Py_XDECREF(fname); | |
729 | Py_XDECREF(cname); |
|
729 | Py_XDECREF(cname); | |
730 | Py_XDECREF(entry); |
|
730 | Py_XDECREF(entry); | |
731 | Py_XDECREF(parents); |
|
731 | Py_XDECREF(parents); | |
732 | return ret; |
|
732 | return ret; | |
733 | } |
|
733 | } | |
734 |
|
734 | |||
735 | /* |
|
735 | /* | |
736 | * Efficiently pack a dirstate object into its on-disk format. |
|
736 | * Efficiently pack a dirstate object into its on-disk format. | |
737 | */ |
|
737 | */ | |
738 | static PyObject *pack_dirstate(PyObject *self, PyObject *args) |
|
738 | static PyObject *pack_dirstate(PyObject *self, PyObject *args) | |
739 | { |
|
739 | { | |
740 | PyObject *packobj = NULL; |
|
740 | PyObject *packobj = NULL; | |
741 | PyObject *map, *copymap, *pl, *mtime_unset = NULL; |
|
741 | PyObject *map, *copymap, *pl, *mtime_unset = NULL; | |
742 | Py_ssize_t nbytes, pos, l; |
|
742 | Py_ssize_t nbytes, pos, l; | |
743 | PyObject *k, *v = NULL, *pn; |
|
743 | PyObject *k, *v = NULL, *pn; | |
744 | char *p, *s; |
|
744 | char *p, *s; | |
745 | int now; |
|
745 | int now; | |
746 |
|
746 | |||
747 | if (!PyArg_ParseTuple(args, "O!O!O!i:pack_dirstate", &PyDict_Type, &map, |
|
747 | if (!PyArg_ParseTuple(args, "O!O!O!i:pack_dirstate", &PyDict_Type, &map, | |
748 | &PyDict_Type, ©map, &PyTuple_Type, &pl, |
|
748 | &PyDict_Type, ©map, &PyTuple_Type, &pl, | |
749 | &now)) { |
|
749 | &now)) { | |
750 | return NULL; |
|
750 | return NULL; | |
751 | } |
|
751 | } | |
752 |
|
752 | |||
753 | if (PyTuple_Size(pl) != 2) { |
|
753 | if (PyTuple_Size(pl) != 2) { | |
754 | PyErr_SetString(PyExc_TypeError, "expected 2-element tuple"); |
|
754 | PyErr_SetString(PyExc_TypeError, "expected 2-element tuple"); | |
755 | return NULL; |
|
755 | return NULL; | |
756 | } |
|
756 | } | |
757 |
|
757 | |||
758 | /* Figure out how much we need to allocate. */ |
|
758 | /* Figure out how much we need to allocate. */ | |
759 | for (nbytes = 40, pos = 0; PyDict_Next(map, &pos, &k, &v);) { |
|
759 | for (nbytes = 40, pos = 0; PyDict_Next(map, &pos, &k, &v);) { | |
760 | PyObject *c; |
|
760 | PyObject *c; | |
761 | if (!PyBytes_Check(k)) { |
|
761 | if (!PyBytes_Check(k)) { | |
762 | PyErr_SetString(PyExc_TypeError, "expected string key"); |
|
762 | PyErr_SetString(PyExc_TypeError, "expected string key"); | |
763 | goto bail; |
|
763 | goto bail; | |
764 | } |
|
764 | } | |
765 | nbytes += PyBytes_GET_SIZE(k) + 17; |
|
765 | nbytes += PyBytes_GET_SIZE(k) + 17; | |
766 | c = PyDict_GetItem(copymap, k); |
|
766 | c = PyDict_GetItem(copymap, k); | |
767 | if (c) { |
|
767 | if (c) { | |
768 | if (!PyBytes_Check(c)) { |
|
768 | if (!PyBytes_Check(c)) { | |
769 | PyErr_SetString(PyExc_TypeError, |
|
769 | PyErr_SetString(PyExc_TypeError, | |
770 | "expected string key"); |
|
770 | "expected string key"); | |
771 | goto bail; |
|
771 | goto bail; | |
772 | } |
|
772 | } | |
773 | nbytes += PyBytes_GET_SIZE(c) + 1; |
|
773 | nbytes += PyBytes_GET_SIZE(c) + 1; | |
774 | } |
|
774 | } | |
775 | } |
|
775 | } | |
776 |
|
776 | |||
777 | packobj = PyBytes_FromStringAndSize(NULL, nbytes); |
|
777 | packobj = PyBytes_FromStringAndSize(NULL, nbytes); | |
778 | if (packobj == NULL) { |
|
778 | if (packobj == NULL) { | |
779 | goto bail; |
|
779 | goto bail; | |
780 | } |
|
780 | } | |
781 |
|
781 | |||
782 | p = PyBytes_AS_STRING(packobj); |
|
782 | p = PyBytes_AS_STRING(packobj); | |
783 |
|
783 | |||
784 | pn = PyTuple_GET_ITEM(pl, 0); |
|
784 | pn = PyTuple_GET_ITEM(pl, 0); | |
785 | if (PyBytes_AsStringAndSize(pn, &s, &l) == -1 || l != 20) { |
|
785 | if (PyBytes_AsStringAndSize(pn, &s, &l) == -1 || l != 20) { | |
786 | PyErr_SetString(PyExc_TypeError, "expected a 20-byte hash"); |
|
786 | PyErr_SetString(PyExc_TypeError, "expected a 20-byte hash"); | |
787 | goto bail; |
|
787 | goto bail; | |
788 | } |
|
788 | } | |
789 | memcpy(p, s, l); |
|
789 | memcpy(p, s, l); | |
790 | p += 20; |
|
790 | p += 20; | |
791 | pn = PyTuple_GET_ITEM(pl, 1); |
|
791 | pn = PyTuple_GET_ITEM(pl, 1); | |
792 | if (PyBytes_AsStringAndSize(pn, &s, &l) == -1 || l != 20) { |
|
792 | if (PyBytes_AsStringAndSize(pn, &s, &l) == -1 || l != 20) { | |
793 | PyErr_SetString(PyExc_TypeError, "expected a 20-byte hash"); |
|
793 | PyErr_SetString(PyExc_TypeError, "expected a 20-byte hash"); | |
794 | goto bail; |
|
794 | goto bail; | |
795 | } |
|
795 | } | |
796 | memcpy(p, s, l); |
|
796 | memcpy(p, s, l); | |
797 | p += 20; |
|
797 | p += 20; | |
798 |
|
798 | |||
799 | for (pos = 0; PyDict_Next(map, &pos, &k, &v);) { |
|
799 | for (pos = 0; PyDict_Next(map, &pos, &k, &v);) { | |
800 | dirstateItemObject *tuple; |
|
800 | dirstateItemObject *tuple; | |
801 | char state; |
|
801 | char state; | |
802 | int mode, size, mtime; |
|
802 | int mode, size, mtime; | |
803 | Py_ssize_t len, l; |
|
803 | Py_ssize_t len, l; | |
804 | PyObject *o; |
|
804 | PyObject *o; | |
805 | char *t; |
|
805 | char *t; | |
806 |
|
806 | |||
807 | if (!dirstate_tuple_check(v)) { |
|
807 | if (!dirstate_tuple_check(v)) { | |
808 | PyErr_SetString(PyExc_TypeError, |
|
808 | PyErr_SetString(PyExc_TypeError, | |
809 | "expected a dirstate tuple"); |
|
809 | "expected a dirstate tuple"); | |
810 | goto bail; |
|
810 | goto bail; | |
811 | } |
|
811 | } | |
812 | tuple = (dirstateItemObject *)v; |
|
812 | tuple = (dirstateItemObject *)v; | |
813 |
|
813 | |||
814 | state = dirstate_item_c_v1_state(tuple); |
|
814 | state = dirstate_item_c_v1_state(tuple); | |
815 | mode = dirstate_item_c_v1_mode(tuple); |
|
815 | mode = dirstate_item_c_v1_mode(tuple); | |
816 | size = dirstate_item_c_v1_size(tuple); |
|
816 | size = dirstate_item_c_v1_size(tuple); | |
817 | mtime = dirstate_item_c_v1_mtime(tuple); |
|
817 | mtime = dirstate_item_c_v1_mtime(tuple); | |
818 | if (state == 'n' && mtime == now) { |
|
818 | if (state == 'n' && mtime == now) { | |
819 | /* See pure/parsers.py:pack_dirstate for why we do |
|
819 | /* See pure/parsers.py:pack_dirstate for why we do | |
820 | * this. */ |
|
820 | * this. */ | |
821 | mtime = -1; |
|
821 | mtime = -1; | |
822 | mtime_unset = (PyObject *)dirstate_item_from_v1_data( |
|
822 | mtime_unset = (PyObject *)dirstate_item_from_v1_data( | |
823 | state, mode, size, mtime); |
|
823 | state, mode, size, mtime); | |
824 | if (!mtime_unset) { |
|
824 | if (!mtime_unset) { | |
825 | goto bail; |
|
825 | goto bail; | |
826 | } |
|
826 | } | |
827 | if (PyDict_SetItem(map, k, mtime_unset) == -1) { |
|
827 | if (PyDict_SetItem(map, k, mtime_unset) == -1) { | |
828 | goto bail; |
|
828 | goto bail; | |
829 | } |
|
829 | } | |
830 | Py_DECREF(mtime_unset); |
|
830 | Py_DECREF(mtime_unset); | |
831 | mtime_unset = NULL; |
|
831 | mtime_unset = NULL; | |
832 | } |
|
832 | } | |
833 | *p++ = state; |
|
833 | *p++ = state; | |
834 | putbe32((uint32_t)mode, p); |
|
834 | putbe32((uint32_t)mode, p); | |
835 | putbe32((uint32_t)size, p + 4); |
|
835 | putbe32((uint32_t)size, p + 4); | |
836 | putbe32((uint32_t)mtime, p + 8); |
|
836 | putbe32((uint32_t)mtime, p + 8); | |
837 | t = p + 12; |
|
837 | t = p + 12; | |
838 | p += 16; |
|
838 | p += 16; | |
839 | len = PyBytes_GET_SIZE(k); |
|
839 | len = PyBytes_GET_SIZE(k); | |
840 | memcpy(p, PyBytes_AS_STRING(k), len); |
|
840 | memcpy(p, PyBytes_AS_STRING(k), len); | |
841 | p += len; |
|
841 | p += len; | |
842 | o = PyDict_GetItem(copymap, k); |
|
842 | o = PyDict_GetItem(copymap, k); | |
843 | if (o) { |
|
843 | if (o) { | |
844 | *p++ = '\0'; |
|
844 | *p++ = '\0'; | |
845 | l = PyBytes_GET_SIZE(o); |
|
845 | l = PyBytes_GET_SIZE(o); | |
846 | memcpy(p, PyBytes_AS_STRING(o), l); |
|
846 | memcpy(p, PyBytes_AS_STRING(o), l); | |
847 | p += l; |
|
847 | p += l; | |
848 | len += l + 1; |
|
848 | len += l + 1; | |
849 | } |
|
849 | } | |
850 | putbe32((uint32_t)len, t); |
|
850 | putbe32((uint32_t)len, t); | |
851 | } |
|
851 | } | |
852 |
|
852 | |||
853 | pos = p - PyBytes_AS_STRING(packobj); |
|
853 | pos = p - PyBytes_AS_STRING(packobj); | |
854 | if (pos != nbytes) { |
|
854 | if (pos != nbytes) { | |
855 | PyErr_Format(PyExc_SystemError, "bad dirstate size: %ld != %ld", |
|
855 | PyErr_Format(PyExc_SystemError, "bad dirstate size: %ld != %ld", | |
856 | (long)pos, (long)nbytes); |
|
856 | (long)pos, (long)nbytes); | |
857 | goto bail; |
|
857 | goto bail; | |
858 | } |
|
858 | } | |
859 |
|
859 | |||
860 | return packobj; |
|
860 | return packobj; | |
861 | bail: |
|
861 | bail: | |
862 | Py_XDECREF(mtime_unset); |
|
862 | Py_XDECREF(mtime_unset); | |
863 | Py_XDECREF(packobj); |
|
863 | Py_XDECREF(packobj); | |
864 | Py_XDECREF(v); |
|
864 | Py_XDECREF(v); | |
865 | return NULL; |
|
865 | return NULL; | |
866 | } |
|
866 | } | |
867 |
|
867 | |||
868 | #define BUMPED_FIX 1 |
|
868 | #define BUMPED_FIX 1 | |
869 | #define USING_SHA_256 2 |
|
869 | #define USING_SHA_256 2 | |
870 | #define FM1_HEADER_SIZE (4 + 8 + 2 + 2 + 1 + 1 + 1) |
|
870 | #define FM1_HEADER_SIZE (4 + 8 + 2 + 2 + 1 + 1 + 1) | |
871 |
|
871 | |||
872 | static PyObject *readshas(const char *source, unsigned char num, |
|
872 | static PyObject *readshas(const char *source, unsigned char num, | |
873 | Py_ssize_t hashwidth) |
|
873 | Py_ssize_t hashwidth) | |
874 | { |
|
874 | { | |
875 | int i; |
|
875 | int i; | |
876 | PyObject *list = PyTuple_New(num); |
|
876 | PyObject *list = PyTuple_New(num); | |
877 | if (list == NULL) { |
|
877 | if (list == NULL) { | |
878 | return NULL; |
|
878 | return NULL; | |
879 | } |
|
879 | } | |
880 | for (i = 0; i < num; i++) { |
|
880 | for (i = 0; i < num; i++) { | |
881 | PyObject *hash = PyBytes_FromStringAndSize(source, hashwidth); |
|
881 | PyObject *hash = PyBytes_FromStringAndSize(source, hashwidth); | |
882 | if (hash == NULL) { |
|
882 | if (hash == NULL) { | |
883 | Py_DECREF(list); |
|
883 | Py_DECREF(list); | |
884 | return NULL; |
|
884 | return NULL; | |
885 | } |
|
885 | } | |
886 | PyTuple_SET_ITEM(list, i, hash); |
|
886 | PyTuple_SET_ITEM(list, i, hash); | |
887 | source += hashwidth; |
|
887 | source += hashwidth; | |
888 | } |
|
888 | } | |
889 | return list; |
|
889 | return list; | |
890 | } |
|
890 | } | |
891 |
|
891 | |||
892 | static PyObject *fm1readmarker(const char *databegin, const char *dataend, |
|
892 | static PyObject *fm1readmarker(const char *databegin, const char *dataend, | |
893 | uint32_t *msize) |
|
893 | uint32_t *msize) | |
894 | { |
|
894 | { | |
895 | const char *data = databegin; |
|
895 | const char *data = databegin; | |
896 | const char *meta; |
|
896 | const char *meta; | |
897 |
|
897 | |||
898 | double mtime; |
|
898 | double mtime; | |
899 | int16_t tz; |
|
899 | int16_t tz; | |
900 | uint16_t flags; |
|
900 | uint16_t flags; | |
901 | unsigned char nsuccs, nparents, nmetadata; |
|
901 | unsigned char nsuccs, nparents, nmetadata; | |
902 | Py_ssize_t hashwidth = 20; |
|
902 | Py_ssize_t hashwidth = 20; | |
903 |
|
903 | |||
904 | PyObject *prec = NULL, *parents = NULL, *succs = NULL; |
|
904 | PyObject *prec = NULL, *parents = NULL, *succs = NULL; | |
905 | PyObject *metadata = NULL, *ret = NULL; |
|
905 | PyObject *metadata = NULL, *ret = NULL; | |
906 | int i; |
|
906 | int i; | |
907 |
|
907 | |||
908 | if (data + FM1_HEADER_SIZE > dataend) { |
|
908 | if (data + FM1_HEADER_SIZE > dataend) { | |
909 | goto overflow; |
|
909 | goto overflow; | |
910 | } |
|
910 | } | |
911 |
|
911 | |||
912 | *msize = getbe32(data); |
|
912 | *msize = getbe32(data); | |
913 | data += 4; |
|
913 | data += 4; | |
914 | mtime = getbefloat64(data); |
|
914 | mtime = getbefloat64(data); | |
915 | data += 8; |
|
915 | data += 8; | |
916 | tz = getbeint16(data); |
|
916 | tz = getbeint16(data); | |
917 | data += 2; |
|
917 | data += 2; | |
918 | flags = getbeuint16(data); |
|
918 | flags = getbeuint16(data); | |
919 | data += 2; |
|
919 | data += 2; | |
920 |
|
920 | |||
921 | if (flags & USING_SHA_256) { |
|
921 | if (flags & USING_SHA_256) { | |
922 | hashwidth = 32; |
|
922 | hashwidth = 32; | |
923 | } |
|
923 | } | |
924 |
|
924 | |||
925 | nsuccs = (unsigned char)(*data++); |
|
925 | nsuccs = (unsigned char)(*data++); | |
926 | nparents = (unsigned char)(*data++); |
|
926 | nparents = (unsigned char)(*data++); | |
927 | nmetadata = (unsigned char)(*data++); |
|
927 | nmetadata = (unsigned char)(*data++); | |
928 |
|
928 | |||
929 | if (databegin + *msize > dataend) { |
|
929 | if (databegin + *msize > dataend) { | |
930 | goto overflow; |
|
930 | goto overflow; | |
931 | } |
|
931 | } | |
932 | dataend = databegin + *msize; /* narrow down to marker size */ |
|
932 | dataend = databegin + *msize; /* narrow down to marker size */ | |
933 |
|
933 | |||
934 | if (data + hashwidth > dataend) { |
|
934 | if (data + hashwidth > dataend) { | |
935 | goto overflow; |
|
935 | goto overflow; | |
936 | } |
|
936 | } | |
937 | prec = PyBytes_FromStringAndSize(data, hashwidth); |
|
937 | prec = PyBytes_FromStringAndSize(data, hashwidth); | |
938 | data += hashwidth; |
|
938 | data += hashwidth; | |
939 | if (prec == NULL) { |
|
939 | if (prec == NULL) { | |
940 | goto bail; |
|
940 | goto bail; | |
941 | } |
|
941 | } | |
942 |
|
942 | |||
943 | if (data + nsuccs * hashwidth > dataend) { |
|
943 | if (data + nsuccs * hashwidth > dataend) { | |
944 | goto overflow; |
|
944 | goto overflow; | |
945 | } |
|
945 | } | |
946 | succs = readshas(data, nsuccs, hashwidth); |
|
946 | succs = readshas(data, nsuccs, hashwidth); | |
947 | if (succs == NULL) { |
|
947 | if (succs == NULL) { | |
948 | goto bail; |
|
948 | goto bail; | |
949 | } |
|
949 | } | |
950 | data += nsuccs * hashwidth; |
|
950 | data += nsuccs * hashwidth; | |
951 |
|
951 | |||
952 | if (nparents == 1 || nparents == 2) { |
|
952 | if (nparents == 1 || nparents == 2) { | |
953 | if (data + nparents * hashwidth > dataend) { |
|
953 | if (data + nparents * hashwidth > dataend) { | |
954 | goto overflow; |
|
954 | goto overflow; | |
955 | } |
|
955 | } | |
956 | parents = readshas(data, nparents, hashwidth); |
|
956 | parents = readshas(data, nparents, hashwidth); | |
957 | if (parents == NULL) { |
|
957 | if (parents == NULL) { | |
958 | goto bail; |
|
958 | goto bail; | |
959 | } |
|
959 | } | |
960 | data += nparents * hashwidth; |
|
960 | data += nparents * hashwidth; | |
961 | } else { |
|
961 | } else { | |
962 | parents = Py_None; |
|
962 | parents = Py_None; | |
963 | Py_INCREF(parents); |
|
963 | Py_INCREF(parents); | |
964 | } |
|
964 | } | |
965 |
|
965 | |||
966 | if (data + 2 * nmetadata > dataend) { |
|
966 | if (data + 2 * nmetadata > dataend) { | |
967 | goto overflow; |
|
967 | goto overflow; | |
968 | } |
|
968 | } | |
969 | meta = data + (2 * nmetadata); |
|
969 | meta = data + (2 * nmetadata); | |
970 | metadata = PyTuple_New(nmetadata); |
|
970 | metadata = PyTuple_New(nmetadata); | |
971 | if (metadata == NULL) { |
|
971 | if (metadata == NULL) { | |
972 | goto bail; |
|
972 | goto bail; | |
973 | } |
|
973 | } | |
974 | for (i = 0; i < nmetadata; i++) { |
|
974 | for (i = 0; i < nmetadata; i++) { | |
975 | PyObject *tmp, *left = NULL, *right = NULL; |
|
975 | PyObject *tmp, *left = NULL, *right = NULL; | |
976 | Py_ssize_t leftsize = (unsigned char)(*data++); |
|
976 | Py_ssize_t leftsize = (unsigned char)(*data++); | |
977 | Py_ssize_t rightsize = (unsigned char)(*data++); |
|
977 | Py_ssize_t rightsize = (unsigned char)(*data++); | |
978 | if (meta + leftsize + rightsize > dataend) { |
|
978 | if (meta + leftsize + rightsize > dataend) { | |
979 | goto overflow; |
|
979 | goto overflow; | |
980 | } |
|
980 | } | |
981 | left = PyBytes_FromStringAndSize(meta, leftsize); |
|
981 | left = PyBytes_FromStringAndSize(meta, leftsize); | |
982 | meta += leftsize; |
|
982 | meta += leftsize; | |
983 | right = PyBytes_FromStringAndSize(meta, rightsize); |
|
983 | right = PyBytes_FromStringAndSize(meta, rightsize); | |
984 | meta += rightsize; |
|
984 | meta += rightsize; | |
985 | tmp = PyTuple_New(2); |
|
985 | tmp = PyTuple_New(2); | |
986 | if (!left || !right || !tmp) { |
|
986 | if (!left || !right || !tmp) { | |
987 | Py_XDECREF(left); |
|
987 | Py_XDECREF(left); | |
988 | Py_XDECREF(right); |
|
988 | Py_XDECREF(right); | |
989 | Py_XDECREF(tmp); |
|
989 | Py_XDECREF(tmp); | |
990 | goto bail; |
|
990 | goto bail; | |
991 | } |
|
991 | } | |
992 | PyTuple_SET_ITEM(tmp, 0, left); |
|
992 | PyTuple_SET_ITEM(tmp, 0, left); | |
993 | PyTuple_SET_ITEM(tmp, 1, right); |
|
993 | PyTuple_SET_ITEM(tmp, 1, right); | |
994 | PyTuple_SET_ITEM(metadata, i, tmp); |
|
994 | PyTuple_SET_ITEM(metadata, i, tmp); | |
995 | } |
|
995 | } | |
996 | ret = Py_BuildValue("(OOHO(di)O)", prec, succs, flags, metadata, mtime, |
|
996 | ret = Py_BuildValue("(OOHO(di)O)", prec, succs, flags, metadata, mtime, | |
997 | (int)tz * 60, parents); |
|
997 | (int)tz * 60, parents); | |
998 | goto bail; /* return successfully */ |
|
998 | goto bail; /* return successfully */ | |
999 |
|
999 | |||
1000 | overflow: |
|
1000 | overflow: | |
1001 | PyErr_SetString(PyExc_ValueError, "overflow in obsstore"); |
|
1001 | PyErr_SetString(PyExc_ValueError, "overflow in obsstore"); | |
1002 | bail: |
|
1002 | bail: | |
1003 | Py_XDECREF(prec); |
|
1003 | Py_XDECREF(prec); | |
1004 | Py_XDECREF(succs); |
|
1004 | Py_XDECREF(succs); | |
1005 | Py_XDECREF(metadata); |
|
1005 | Py_XDECREF(metadata); | |
1006 | Py_XDECREF(parents); |
|
1006 | Py_XDECREF(parents); | |
1007 | return ret; |
|
1007 | return ret; | |
1008 | } |
|
1008 | } | |
1009 |
|
1009 | |||
1010 | static PyObject *fm1readmarkers(PyObject *self, PyObject *args) |
|
1010 | static PyObject *fm1readmarkers(PyObject *self, PyObject *args) | |
1011 | { |
|
1011 | { | |
1012 | const char *data, *dataend; |
|
1012 | const char *data, *dataend; | |
1013 | Py_ssize_t datalen, offset, stop; |
|
1013 | Py_ssize_t datalen, offset, stop; | |
1014 | PyObject *markers = NULL; |
|
1014 | PyObject *markers = NULL; | |
1015 |
|
1015 | |||
1016 | if (!PyArg_ParseTuple(args, PY23("s#nn", "y#nn"), &data, &datalen, |
|
1016 | if (!PyArg_ParseTuple(args, PY23("s#nn", "y#nn"), &data, &datalen, | |
1017 | &offset, &stop)) { |
|
1017 | &offset, &stop)) { | |
1018 | return NULL; |
|
1018 | return NULL; | |
1019 | } |
|
1019 | } | |
1020 | if (offset < 0) { |
|
1020 | if (offset < 0) { | |
1021 | PyErr_SetString(PyExc_ValueError, |
|
1021 | PyErr_SetString(PyExc_ValueError, | |
1022 | "invalid negative offset in fm1readmarkers"); |
|
1022 | "invalid negative offset in fm1readmarkers"); | |
1023 | return NULL; |
|
1023 | return NULL; | |
1024 | } |
|
1024 | } | |
1025 | if (stop > datalen) { |
|
1025 | if (stop > datalen) { | |
1026 | PyErr_SetString( |
|
1026 | PyErr_SetString( | |
1027 | PyExc_ValueError, |
|
1027 | PyExc_ValueError, | |
1028 | "stop longer than data length in fm1readmarkers"); |
|
1028 | "stop longer than data length in fm1readmarkers"); | |
1029 | return NULL; |
|
1029 | return NULL; | |
1030 | } |
|
1030 | } | |
1031 | dataend = data + datalen; |
|
1031 | dataend = data + datalen; | |
1032 | data += offset; |
|
1032 | data += offset; | |
1033 | markers = PyList_New(0); |
|
1033 | markers = PyList_New(0); | |
1034 | if (!markers) { |
|
1034 | if (!markers) { | |
1035 | return NULL; |
|
1035 | return NULL; | |
1036 | } |
|
1036 | } | |
1037 | while (offset < stop) { |
|
1037 | while (offset < stop) { | |
1038 | uint32_t msize; |
|
1038 | uint32_t msize; | |
1039 | int error; |
|
1039 | int error; | |
1040 | PyObject *record = fm1readmarker(data, dataend, &msize); |
|
1040 | PyObject *record = fm1readmarker(data, dataend, &msize); | |
1041 | if (!record) { |
|
1041 | if (!record) { | |
1042 | goto bail; |
|
1042 | goto bail; | |
1043 | } |
|
1043 | } | |
1044 | error = PyList_Append(markers, record); |
|
1044 | error = PyList_Append(markers, record); | |
1045 | Py_DECREF(record); |
|
1045 | Py_DECREF(record); | |
1046 | if (error) { |
|
1046 | if (error) { | |
1047 | goto bail; |
|
1047 | goto bail; | |
1048 | } |
|
1048 | } | |
1049 | data += msize; |
|
1049 | data += msize; | |
1050 | offset += msize; |
|
1050 | offset += msize; | |
1051 | } |
|
1051 | } | |
1052 | return markers; |
|
1052 | return markers; | |
1053 | bail: |
|
1053 | bail: | |
1054 | Py_DECREF(markers); |
|
1054 | Py_DECREF(markers); | |
1055 | return NULL; |
|
1055 | return NULL; | |
1056 | } |
|
1056 | } | |
1057 |
|
1057 | |||
1058 | static char parsers_doc[] = "Efficient content parsing."; |
|
1058 | static char parsers_doc[] = "Efficient content parsing."; | |
1059 |
|
1059 | |||
1060 | PyObject *encodedir(PyObject *self, PyObject *args); |
|
1060 | PyObject *encodedir(PyObject *self, PyObject *args); | |
1061 | PyObject *pathencode(PyObject *self, PyObject *args); |
|
1061 | PyObject *pathencode(PyObject *self, PyObject *args); | |
1062 | PyObject *lowerencode(PyObject *self, PyObject *args); |
|
1062 | PyObject *lowerencode(PyObject *self, PyObject *args); | |
1063 | PyObject *parse_index2(PyObject *self, PyObject *args, PyObject *kwargs); |
|
1063 | PyObject *parse_index2(PyObject *self, PyObject *args, PyObject *kwargs); | |
1064 |
|
1064 | |||
1065 | static PyMethodDef methods[] = { |
|
1065 | static PyMethodDef methods[] = { | |
1066 | {"pack_dirstate", pack_dirstate, METH_VARARGS, "pack a dirstate\n"}, |
|
1066 | {"pack_dirstate", pack_dirstate, METH_VARARGS, "pack a dirstate\n"}, | |
1067 | {"parse_dirstate", parse_dirstate, METH_VARARGS, "parse a dirstate\n"}, |
|
1067 | {"parse_dirstate", parse_dirstate, METH_VARARGS, "parse a dirstate\n"}, | |
1068 | {"parse_index2", (PyCFunction)parse_index2, METH_VARARGS | METH_KEYWORDS, |
|
1068 | {"parse_index2", (PyCFunction)parse_index2, METH_VARARGS | METH_KEYWORDS, | |
1069 | "parse a revlog index\n"}, |
|
1069 | "parse a revlog index\n"}, | |
1070 | {"isasciistr", isasciistr, METH_VARARGS, "check if an ASCII string\n"}, |
|
1070 | {"isasciistr", isasciistr, METH_VARARGS, "check if an ASCII string\n"}, | |
1071 | {"asciilower", asciilower, METH_VARARGS, "lowercase an ASCII string\n"}, |
|
1071 | {"asciilower", asciilower, METH_VARARGS, "lowercase an ASCII string\n"}, | |
1072 | {"asciiupper", asciiupper, METH_VARARGS, "uppercase an ASCII string\n"}, |
|
1072 | {"asciiupper", asciiupper, METH_VARARGS, "uppercase an ASCII string\n"}, | |
1073 | {"dict_new_presized", dict_new_presized, METH_VARARGS, |
|
1073 | {"dict_new_presized", dict_new_presized, METH_VARARGS, | |
1074 | "construct a dict with an expected size\n"}, |
|
1074 | "construct a dict with an expected size\n"}, | |
1075 | {"make_file_foldmap", make_file_foldmap, METH_VARARGS, |
|
1075 | {"make_file_foldmap", make_file_foldmap, METH_VARARGS, | |
1076 | "make file foldmap\n"}, |
|
1076 | "make file foldmap\n"}, | |
1077 | {"jsonescapeu8fast", jsonescapeu8fast, METH_VARARGS, |
|
1077 | {"jsonescapeu8fast", jsonescapeu8fast, METH_VARARGS, | |
1078 | "escape a UTF-8 byte string to JSON (fast path)\n"}, |
|
1078 | "escape a UTF-8 byte string to JSON (fast path)\n"}, | |
1079 | {"encodedir", encodedir, METH_VARARGS, "encodedir a path\n"}, |
|
1079 | {"encodedir", encodedir, METH_VARARGS, "encodedir a path\n"}, | |
1080 | {"pathencode", pathencode, METH_VARARGS, "fncache-encode a path\n"}, |
|
1080 | {"pathencode", pathencode, METH_VARARGS, "fncache-encode a path\n"}, | |
1081 | {"lowerencode", lowerencode, METH_VARARGS, "lower-encode a path\n"}, |
|
1081 | {"lowerencode", lowerencode, METH_VARARGS, "lower-encode a path\n"}, | |
1082 | {"fm1readmarkers", fm1readmarkers, METH_VARARGS, |
|
1082 | {"fm1readmarkers", fm1readmarkers, METH_VARARGS, | |
1083 | "parse v1 obsolete markers\n"}, |
|
1083 | "parse v1 obsolete markers\n"}, | |
1084 | {NULL, NULL}}; |
|
1084 | {NULL, NULL}}; | |
1085 |
|
1085 | |||
1086 | void dirs_module_init(PyObject *mod); |
|
1086 | void dirs_module_init(PyObject *mod); | |
1087 | void manifest_module_init(PyObject *mod); |
|
1087 | void manifest_module_init(PyObject *mod); | |
1088 | void revlog_module_init(PyObject *mod); |
|
1088 | void revlog_module_init(PyObject *mod); | |
1089 |
|
1089 | |||
1090 | static const int version = 20; |
|
1090 | static const int version = 20; | |
1091 |
|
1091 | |||
1092 | static void module_init(PyObject *mod) |
|
1092 | static void module_init(PyObject *mod) | |
1093 | { |
|
1093 | { | |
1094 | PyModule_AddIntConstant(mod, "version", version); |
|
1094 | PyModule_AddIntConstant(mod, "version", version); | |
1095 |
|
1095 | |||
1096 | /* This module constant has two purposes. First, it lets us unit test |
|
1096 | /* This module constant has two purposes. First, it lets us unit test | |
1097 | * the ImportError raised without hard-coding any error text. This |
|
1097 | * the ImportError raised without hard-coding any error text. This | |
1098 | * means we can change the text in the future without breaking tests, |
|
1098 | * means we can change the text in the future without breaking tests, | |
1099 | * even across changesets without a recompile. Second, its presence |
|
1099 | * even across changesets without a recompile. Second, its presence | |
1100 | * can be used to determine whether the version-checking logic is |
|
1100 | * can be used to determine whether the version-checking logic is | |
1101 | * present, which also helps in testing across changesets without a |
|
1101 | * present, which also helps in testing across changesets without a | |
1102 | * recompile. Note that this means the pure-Python version of parsers |
|
1102 | * recompile. Note that this means the pure-Python version of parsers | |
1103 | * should not have this module constant. */ |
|
1103 | * should not have this module constant. */ | |
1104 | PyModule_AddStringConstant(mod, "versionerrortext", versionerrortext); |
|
1104 | PyModule_AddStringConstant(mod, "versionerrortext", versionerrortext); | |
1105 |
|
1105 | |||
1106 | dirs_module_init(mod); |
|
1106 | dirs_module_init(mod); | |
1107 | manifest_module_init(mod); |
|
1107 | manifest_module_init(mod); | |
1108 | revlog_module_init(mod); |
|
1108 | revlog_module_init(mod); | |
1109 |
|
1109 | |||
1110 | if (PyType_Ready(&dirstateItemType) < 0) { |
|
1110 | if (PyType_Ready(&dirstateItemType) < 0) { | |
1111 | return; |
|
1111 | return; | |
1112 | } |
|
1112 | } | |
1113 | Py_INCREF(&dirstateItemType); |
|
1113 | Py_INCREF(&dirstateItemType); | |
1114 | PyModule_AddObject(mod, "DirstateItem", (PyObject *)&dirstateItemType); |
|
1114 | PyModule_AddObject(mod, "DirstateItem", (PyObject *)&dirstateItemType); | |
1115 | } |
|
1115 | } | |
1116 |
|
1116 | |||
1117 | static int check_python_version(void) |
|
1117 | static int check_python_version(void) | |
1118 | { |
|
1118 | { | |
1119 | PyObject *sys = PyImport_ImportModule("sys"), *ver; |
|
1119 | PyObject *sys = PyImport_ImportModule("sys"), *ver; | |
1120 | long hexversion; |
|
1120 | long hexversion; | |
1121 | if (!sys) { |
|
1121 | if (!sys) { | |
1122 | return -1; |
|
1122 | return -1; | |
1123 | } |
|
1123 | } | |
1124 | ver = PyObject_GetAttrString(sys, "hexversion"); |
|
1124 | ver = PyObject_GetAttrString(sys, "hexversion"); | |
1125 | Py_DECREF(sys); |
|
1125 | Py_DECREF(sys); | |
1126 | if (!ver) { |
|
1126 | if (!ver) { | |
1127 | return -1; |
|
1127 | return -1; | |
1128 | } |
|
1128 | } | |
1129 | hexversion = PyInt_AsLong(ver); |
|
1129 | hexversion = PyInt_AsLong(ver); | |
1130 | Py_DECREF(ver); |
|
1130 | Py_DECREF(ver); | |
1131 | /* sys.hexversion is a 32-bit number by default, so the -1 case |
|
1131 | /* sys.hexversion is a 32-bit number by default, so the -1 case | |
1132 | * should only occur in unusual circumstances (e.g. if sys.hexversion |
|
1132 | * should only occur in unusual circumstances (e.g. if sys.hexversion | |
1133 | * is manually set to an invalid value). */ |
|
1133 | * is manually set to an invalid value). */ | |
1134 | if ((hexversion == -1) || (hexversion >> 16 != PY_VERSION_HEX >> 16)) { |
|
1134 | if ((hexversion == -1) || (hexversion >> 16 != PY_VERSION_HEX >> 16)) { | |
1135 | PyErr_Format(PyExc_ImportError, |
|
1135 | PyErr_Format(PyExc_ImportError, | |
1136 | "%s: The Mercurial extension " |
|
1136 | "%s: The Mercurial extension " | |
1137 | "modules were compiled with Python " PY_VERSION |
|
1137 | "modules were compiled with Python " PY_VERSION | |
1138 | ", but " |
|
1138 | ", but " | |
1139 | "Mercurial is currently using Python with " |
|
1139 | "Mercurial is currently using Python with " | |
1140 | "sys.hexversion=%ld: " |
|
1140 | "sys.hexversion=%ld: " | |
1141 | "Python %s\n at: %s", |
|
1141 | "Python %s\n at: %s", | |
1142 | versionerrortext, hexversion, Py_GetVersion(), |
|
1142 | versionerrortext, hexversion, Py_GetVersion(), | |
1143 | Py_GetProgramFullPath()); |
|
1143 | Py_GetProgramFullPath()); | |
1144 | return -1; |
|
1144 | return -1; | |
1145 | } |
|
1145 | } | |
1146 | return 0; |
|
1146 | return 0; | |
1147 | } |
|
1147 | } | |
1148 |
|
1148 | |||
1149 | #ifdef IS_PY3K |
|
1149 | #ifdef IS_PY3K | |
1150 | static struct PyModuleDef parsers_module = {PyModuleDef_HEAD_INIT, "parsers", |
|
1150 | static struct PyModuleDef parsers_module = {PyModuleDef_HEAD_INIT, "parsers", | |
1151 | parsers_doc, -1, methods}; |
|
1151 | parsers_doc, -1, methods}; | |
1152 |
|
1152 | |||
1153 | PyMODINIT_FUNC PyInit_parsers(void) |
|
1153 | PyMODINIT_FUNC PyInit_parsers(void) | |
1154 | { |
|
1154 | { | |
1155 | PyObject *mod; |
|
1155 | PyObject *mod; | |
1156 |
|
1156 | |||
1157 | if (check_python_version() == -1) |
|
1157 | if (check_python_version() == -1) | |
1158 | return NULL; |
|
1158 | return NULL; | |
1159 | mod = PyModule_Create(&parsers_module); |
|
1159 | mod = PyModule_Create(&parsers_module); | |
1160 | module_init(mod); |
|
1160 | module_init(mod); | |
1161 | return mod; |
|
1161 | return mod; | |
1162 | } |
|
1162 | } | |
1163 | #else |
|
1163 | #else | |
1164 | PyMODINIT_FUNC initparsers(void) |
|
1164 | PyMODINIT_FUNC initparsers(void) | |
1165 | { |
|
1165 | { | |
1166 | PyObject *mod; |
|
1166 | PyObject *mod; | |
1167 |
|
1167 | |||
1168 | if (check_python_version() == -1) { |
|
1168 | if (check_python_version() == -1) { | |
1169 | return; |
|
1169 | return; | |
1170 | } |
|
1170 | } | |
1171 | mod = Py_InitModule3("parsers", methods, parsers_doc); |
|
1171 | mod = Py_InitModule3("parsers", methods, parsers_doc); | |
1172 | module_init(mod); |
|
1172 | module_init(mod); | |
1173 | } |
|
1173 | } | |
1174 | #endif |
|
1174 | #endif |
@@ -1,82 +1,83 b'' | |||||
1 | /* |
|
1 | /* | |
2 | util.h - utility functions for interfacing with the various python APIs. |
|
2 | util.h - utility functions for interfacing with the various python APIs. | |
3 |
|
3 | |||
4 | This software may be used and distributed according to the terms of |
|
4 | This software may be used and distributed according to the terms of | |
5 | the GNU General Public License, incorporated herein by reference. |
|
5 | the GNU General Public License, incorporated herein by reference. | |
6 | */ |
|
6 | */ | |
7 |
|
7 | |||
8 | #ifndef _HG_UTIL_H_ |
|
8 | #ifndef _HG_UTIL_H_ | |
9 | #define _HG_UTIL_H_ |
|
9 | #define _HG_UTIL_H_ | |
10 |
|
10 | |||
11 | #include "compat.h" |
|
11 | #include "compat.h" | |
12 |
|
12 | |||
13 | #if PY_MAJOR_VERSION >= 3 |
|
13 | #if PY_MAJOR_VERSION >= 3 | |
14 | #define IS_PY3K |
|
14 | #define IS_PY3K | |
15 | #endif |
|
15 | #endif | |
16 |
|
16 | |||
17 | /* helper to switch things like string literal depending on Python version */ |
|
17 | /* helper to switch things like string literal depending on Python version */ | |
18 | #ifdef IS_PY3K |
|
18 | #ifdef IS_PY3K | |
19 | #define PY23(py2, py3) py3 |
|
19 | #define PY23(py2, py3) py3 | |
20 | #else |
|
20 | #else | |
21 | #define PY23(py2, py3) py2 |
|
21 | #define PY23(py2, py3) py2 | |
22 | #endif |
|
22 | #endif | |
23 |
|
23 | |||
24 | /* clang-format off */ |
|
24 | /* clang-format off */ | |
25 | typedef struct { |
|
25 | typedef struct { | |
26 | PyObject_HEAD |
|
26 | PyObject_HEAD | |
27 | unsigned char flags; |
|
27 | unsigned char flags; | |
28 | int mode; |
|
28 | int mode; | |
29 | int size; |
|
29 | int size; | |
30 | int mtime; |
|
30 | int mtime; | |
31 | } dirstateItemObject; |
|
31 | } dirstateItemObject; | |
32 | /* clang-format on */ |
|
32 | /* clang-format on */ | |
33 |
|
33 | |||
34 | static const unsigned char dirstate_flag_wc_tracked = 1; |
|
34 | static const unsigned char dirstate_flag_wc_tracked = 1; | |
35 | static const unsigned char dirstate_flag_p1_tracked = 1 << 1; |
|
35 | static const unsigned char dirstate_flag_p1_tracked = 1 << 1; | |
36 | static const unsigned char dirstate_flag_p2_info = 1 << 2; |
|
36 | static const unsigned char dirstate_flag_p2_info = 1 << 2; | |
37 | static const unsigned char dirstate_flag_has_meaningful_data = 1 << 3; |
|
37 | static const unsigned char dirstate_flag_has_meaningful_data = 1 << 3; | |
38 |
static const unsigned char dirstate_flag_has_ |
|
38 | static const unsigned char dirstate_flag_has_file_mtime = 1 << 4; | |
39 |
static const unsigned char dirstate_flag_ |
|
39 | static const unsigned char dirstate_flag_has_directory_mtime = 1 << 5; | |
40 |
static const unsigned char dirstate_flag_mode_ |
|
40 | static const unsigned char dirstate_flag_mode_exec_perm = 1 << 6; | |
|
41 | static const unsigned char dirstate_flag_mode_is_symlink = 1 << 7; | |||
41 |
|
42 | |||
42 | extern PyTypeObject dirstateItemType; |
|
43 | extern PyTypeObject dirstateItemType; | |
43 | #define dirstate_tuple_check(op) (Py_TYPE(op) == &dirstateItemType) |
|
44 | #define dirstate_tuple_check(op) (Py_TYPE(op) == &dirstateItemType) | |
44 |
|
45 | |||
45 | #ifndef MIN |
|
46 | #ifndef MIN | |
46 | #define MIN(a, b) (((a) < (b)) ? (a) : (b)) |
|
47 | #define MIN(a, b) (((a) < (b)) ? (a) : (b)) | |
47 | #endif |
|
48 | #endif | |
48 | /* VC9 doesn't include bool and lacks stdbool.h based on my searching */ |
|
49 | /* VC9 doesn't include bool and lacks stdbool.h based on my searching */ | |
49 | #if defined(_MSC_VER) || __STDC_VERSION__ < 199901L |
|
50 | #if defined(_MSC_VER) || __STDC_VERSION__ < 199901L | |
50 | #define true 1 |
|
51 | #define true 1 | |
51 | #define false 0 |
|
52 | #define false 0 | |
52 | typedef unsigned char bool; |
|
53 | typedef unsigned char bool; | |
53 | #else |
|
54 | #else | |
54 | #include <stdbool.h> |
|
55 | #include <stdbool.h> | |
55 | #endif |
|
56 | #endif | |
56 |
|
57 | |||
57 | static inline PyObject *_dict_new_presized(Py_ssize_t expected_size) |
|
58 | static inline PyObject *_dict_new_presized(Py_ssize_t expected_size) | |
58 | { |
|
59 | { | |
59 | /* _PyDict_NewPresized expects a minused parameter, but it actually |
|
60 | /* _PyDict_NewPresized expects a minused parameter, but it actually | |
60 | creates a dictionary that's the nearest power of two bigger than the |
|
61 | creates a dictionary that's the nearest power of two bigger than the | |
61 | parameter. For example, with the initial minused = 1000, the |
|
62 | parameter. For example, with the initial minused = 1000, the | |
62 | dictionary created has size 1024. Of course in a lot of cases that |
|
63 | dictionary created has size 1024. Of course in a lot of cases that | |
63 | can be greater than the maximum load factor Python's dict object |
|
64 | can be greater than the maximum load factor Python's dict object | |
64 | expects (= 2/3), so as soon as we cross the threshold we'll resize |
|
65 | expects (= 2/3), so as soon as we cross the threshold we'll resize | |
65 | anyway. So create a dictionary that's at least 3/2 the size. */ |
|
66 | anyway. So create a dictionary that's at least 3/2 the size. */ | |
66 | return _PyDict_NewPresized(((1 + expected_size) / 2) * 3); |
|
67 | return _PyDict_NewPresized(((1 + expected_size) / 2) * 3); | |
67 | } |
|
68 | } | |
68 |
|
69 | |||
69 | /* Convert a PyInt or PyLong to a long. Returns false if there is an |
|
70 | /* Convert a PyInt or PyLong to a long. Returns false if there is an | |
70 | error, in which case an exception will already have been set. */ |
|
71 | error, in which case an exception will already have been set. */ | |
71 | static inline bool pylong_to_long(PyObject *pylong, long *out) |
|
72 | static inline bool pylong_to_long(PyObject *pylong, long *out) | |
72 | { |
|
73 | { | |
73 | *out = PyLong_AsLong(pylong); |
|
74 | *out = PyLong_AsLong(pylong); | |
74 | /* Fast path to avoid hitting PyErr_Occurred if the value was obviously |
|
75 | /* Fast path to avoid hitting PyErr_Occurred if the value was obviously | |
75 | * not an error. */ |
|
76 | * not an error. */ | |
76 | if (*out != -1) { |
|
77 | if (*out != -1) { | |
77 | return true; |
|
78 | return true; | |
78 | } |
|
79 | } | |
79 | return PyErr_Occurred() == NULL; |
|
80 | return PyErr_Occurred() == NULL; | |
80 | } |
|
81 | } | |
81 |
|
82 | |||
82 | #endif /* _HG_UTIL_H_ */ |
|
83 | #endif /* _HG_UTIL_H_ */ |
@@ -1,503 +1,516 b'' | |||||
1 | The *dirstate* is what Mercurial uses internally to track |
|
1 | The *dirstate* is what Mercurial uses internally to track | |
2 | the state of files in the working directory, |
|
2 | the state of files in the working directory, | |
3 | such as set by commands like `hg add` and `hg rm`. |
|
3 | such as set by commands like `hg add` and `hg rm`. | |
4 | It also contains some cached data that help make `hg status` faster. |
|
4 | It also contains some cached data that help make `hg status` faster. | |
5 | The name refers both to `.hg/dirstate` on the filesystem |
|
5 | The name refers both to `.hg/dirstate` on the filesystem | |
6 | and the corresponding data structure in memory while a Mercurial process |
|
6 | and the corresponding data structure in memory while a Mercurial process | |
7 | is running. |
|
7 | is running. | |
8 |
|
8 | |||
9 | The original file format, retroactively dubbed `dirstate-v1`, |
|
9 | The original file format, retroactively dubbed `dirstate-v1`, | |
10 | is described at https://www.mercurial-scm.org/wiki/DirState. |
|
10 | is described at https://www.mercurial-scm.org/wiki/DirState. | |
11 | It is made of a flat sequence of unordered variable-size entries, |
|
11 | It is made of a flat sequence of unordered variable-size entries, | |
12 | so accessing any information in it requires parsing all of it. |
|
12 | so accessing any information in it requires parsing all of it. | |
13 | Similarly, saving changes requires rewriting the entire file. |
|
13 | Similarly, saving changes requires rewriting the entire file. | |
14 |
|
14 | |||
15 | The newer `dirsate-v2` file format is designed to fix these limitations |
|
15 | The newer `dirsate-v2` file format is designed to fix these limitations | |
16 | and make `hg status` faster. |
|
16 | and make `hg status` faster. | |
17 |
|
17 | |||
18 | User guide |
|
18 | User guide | |
19 | ========== |
|
19 | ========== | |
20 |
|
20 | |||
21 | Compatibility |
|
21 | Compatibility | |
22 | ------------- |
|
22 | ------------- | |
23 |
|
23 | |||
24 | The file format is experimental and may still change. |
|
24 | The file format is experimental and may still change. | |
25 | Different versions of Mercurial may not be compatible with each other |
|
25 | Different versions of Mercurial may not be compatible with each other | |
26 | when working on a local repository that uses this format. |
|
26 | when working on a local repository that uses this format. | |
27 | When using an incompatible version with the experimental format, |
|
27 | When using an incompatible version with the experimental format, | |
28 | anything can happen including data corruption. |
|
28 | anything can happen including data corruption. | |
29 |
|
29 | |||
30 | Since the dirstate is entirely local and not relevant to the wire protocol, |
|
30 | Since the dirstate is entirely local and not relevant to the wire protocol, | |
31 | `dirstate-v2` does not affect compatibility with remote Mercurial versions. |
|
31 | `dirstate-v2` does not affect compatibility with remote Mercurial versions. | |
32 |
|
32 | |||
33 | When `share-safe` is enabled, different repositories sharing the same store |
|
33 | When `share-safe` is enabled, different repositories sharing the same store | |
34 | can use different dirstate formats. |
|
34 | can use different dirstate formats. | |
35 |
|
35 | |||
36 | Enabling `dirsate-v2` for new local repositories |
|
36 | Enabling `dirsate-v2` for new local repositories | |
37 | ------------------------------------------------ |
|
37 | ------------------------------------------------ | |
38 |
|
38 | |||
39 | When creating a new local repository such as with `hg init` or `hg clone`, |
|
39 | When creating a new local repository such as with `hg init` or `hg clone`, | |
40 | the `exp-dirstate-v2` boolean in the `format` configuration section |
|
40 | the `exp-dirstate-v2` boolean in the `format` configuration section | |
41 | controls whether to use this file format. |
|
41 | controls whether to use this file format. | |
42 | This is disabled by default as of this writing. |
|
42 | This is disabled by default as of this writing. | |
43 | To enable it for a single repository, run for example:: |
|
43 | To enable it for a single repository, run for example:: | |
44 |
|
44 | |||
45 | $ hg init my-project --config format.exp-dirstate-v2=1 |
|
45 | $ hg init my-project --config format.exp-dirstate-v2=1 | |
46 |
|
46 | |||
47 | Checking the format of an existing local repsitory |
|
47 | Checking the format of an existing local repsitory | |
48 | -------------------------------------------------- |
|
48 | -------------------------------------------------- | |
49 |
|
49 | |||
50 | The `debugformat` commands prints information about |
|
50 | The `debugformat` commands prints information about | |
51 | which of multiple optional formats are used in the current repository, |
|
51 | which of multiple optional formats are used in the current repository, | |
52 | including `dirstate-v2`:: |
|
52 | including `dirstate-v2`:: | |
53 |
|
53 | |||
54 | $ hg debugformat |
|
54 | $ hg debugformat | |
55 | format-variant repo |
|
55 | format-variant repo | |
56 | fncache: yes |
|
56 | fncache: yes | |
57 | dirstate-v2: yes |
|
57 | dirstate-v2: yes | |
58 | [β¦] |
|
58 | [β¦] | |
59 |
|
59 | |||
60 | Upgrading or downgrading an existing local repository |
|
60 | Upgrading or downgrading an existing local repository | |
61 | ----------------------------------------------------- |
|
61 | ----------------------------------------------------- | |
62 |
|
62 | |||
63 | The `debugupgrade` command does various upgrades or downgrades |
|
63 | The `debugupgrade` command does various upgrades or downgrades | |
64 | on a local repository |
|
64 | on a local repository | |
65 | based on the current Mercurial version and on configuration. |
|
65 | based on the current Mercurial version and on configuration. | |
66 | The same `format.exp-dirstate-v2` configuration is used again. |
|
66 | The same `format.exp-dirstate-v2` configuration is used again. | |
67 |
|
67 | |||
68 | Example to upgrade:: |
|
68 | Example to upgrade:: | |
69 |
|
69 | |||
70 | $ hg debugupgrade --config format.exp-dirstate-v2=1 |
|
70 | $ hg debugupgrade --config format.exp-dirstate-v2=1 | |
71 |
|
71 | |||
72 | Example to downgrade to `dirstate-v1`:: |
|
72 | Example to downgrade to `dirstate-v1`:: | |
73 |
|
73 | |||
74 | $ hg debugupgrade --config format.exp-dirstate-v2=0 |
|
74 | $ hg debugupgrade --config format.exp-dirstate-v2=0 | |
75 |
|
75 | |||
76 | Both of this commands do nothing but print a list of proposed changes, |
|
76 | Both of this commands do nothing but print a list of proposed changes, | |
77 | which may include changes unrelated to the dirstate. |
|
77 | which may include changes unrelated to the dirstate. | |
78 | Those other changes are controlled by their own configuration keys. |
|
78 | Those other changes are controlled by their own configuration keys. | |
79 | Add `--run` to a command to actually apply the proposed changes. |
|
79 | Add `--run` to a command to actually apply the proposed changes. | |
80 |
|
80 | |||
81 | Backups of `.hg/requires` and `.hg/dirstate` are created |
|
81 | Backups of `.hg/requires` and `.hg/dirstate` are created | |
82 | in a `.hg/upgradebackup.*` directory. |
|
82 | in a `.hg/upgradebackup.*` directory. | |
83 | If something goes wrong, restoring those files should undo the change. |
|
83 | If something goes wrong, restoring those files should undo the change. | |
84 |
|
84 | |||
85 | Note that upgrading affects compatibility with older versions of Mercurial |
|
85 | Note that upgrading affects compatibility with older versions of Mercurial | |
86 | as noted above. |
|
86 | as noted above. | |
87 | This can be relevant when a repositoryβs files are on a USB drive |
|
87 | This can be relevant when a repositoryβs files are on a USB drive | |
88 | or some other removable media, or shared over the network, etc. |
|
88 | or some other removable media, or shared over the network, etc. | |
89 |
|
89 | |||
90 | Internal filesystem representation |
|
90 | Internal filesystem representation | |
91 | ================================== |
|
91 | ================================== | |
92 |
|
92 | |||
93 | Requirements file |
|
93 | Requirements file | |
94 | ----------------- |
|
94 | ----------------- | |
95 |
|
95 | |||
96 | The `.hg/requires` file indicates which of various optional file formats |
|
96 | The `.hg/requires` file indicates which of various optional file formats | |
97 | are used by a given repository. |
|
97 | are used by a given repository. | |
98 | Mercurial aborts when seeing a requirement it does not know about, |
|
98 | Mercurial aborts when seeing a requirement it does not know about, | |
99 | which avoids older version accidentally messing up a respository |
|
99 | which avoids older version accidentally messing up a respository | |
100 | that uses a format that was introduced later. |
|
100 | that uses a format that was introduced later. | |
101 | For versions that do support a format, the presence or absence of |
|
101 | For versions that do support a format, the presence or absence of | |
102 | the corresponding requirement indicates whether to use that format. |
|
102 | the corresponding requirement indicates whether to use that format. | |
103 |
|
103 | |||
104 | When the file contains a `exp-dirstate-v2` line, |
|
104 | When the file contains a `exp-dirstate-v2` line, | |
105 | the `dirstate-v2` format is used. |
|
105 | the `dirstate-v2` format is used. | |
106 | With no such line `dirstate-v1` is used. |
|
106 | With no such line `dirstate-v1` is used. | |
107 |
|
107 | |||
108 | High level description |
|
108 | High level description | |
109 | ---------------------- |
|
109 | ---------------------- | |
110 |
|
110 | |||
111 | Whereas `dirstate-v1` uses a single `.hg/disrtate` file, |
|
111 | Whereas `dirstate-v1` uses a single `.hg/disrtate` file, | |
112 | in `dirstate-v2` that file is a "docket" file |
|
112 | in `dirstate-v2` that file is a "docket" file | |
113 | that only contains some metadata |
|
113 | that only contains some metadata | |
114 | and points to separate data file named `.hg/dirstate.{ID}`, |
|
114 | and points to separate data file named `.hg/dirstate.{ID}`, | |
115 | where `{ID}` is a random identifier. |
|
115 | where `{ID}` is a random identifier. | |
116 |
|
116 | |||
117 | This separation allows making data files append-only |
|
117 | This separation allows making data files append-only | |
118 | and therefore safer to memory-map. |
|
118 | and therefore safer to memory-map. | |
119 | Creating a new data file (occasionally to clean up unused data) |
|
119 | Creating a new data file (occasionally to clean up unused data) | |
120 | can be done with a different ID |
|
120 | can be done with a different ID | |
121 | without disrupting another Mercurial process |
|
121 | without disrupting another Mercurial process | |
122 | that could still be using the previous data file. |
|
122 | that could still be using the previous data file. | |
123 |
|
123 | |||
124 | Both files have a format designed to reduce the need for parsing, |
|
124 | Both files have a format designed to reduce the need for parsing, | |
125 | by using fixed-size binary components as much as possible. |
|
125 | by using fixed-size binary components as much as possible. | |
126 | For data that is not fixed-size, |
|
126 | For data that is not fixed-size, | |
127 | references to other parts of a file can be made by storing "pseudo-pointers": |
|
127 | references to other parts of a file can be made by storing "pseudo-pointers": | |
128 | integers counted in bytes from the start of a file. |
|
128 | integers counted in bytes from the start of a file. | |
129 | For read-only access no data structure is needed, |
|
129 | For read-only access no data structure is needed, | |
130 | only a bytes buffer (possibly memory-mapped directly from the filesystem) |
|
130 | only a bytes buffer (possibly memory-mapped directly from the filesystem) | |
131 | with specific parts read on demand. |
|
131 | with specific parts read on demand. | |
132 |
|
132 | |||
133 | The data file contains "nodes" organized in a tree. |
|
133 | The data file contains "nodes" organized in a tree. | |
134 | Each node represents a file or directory inside the working directory |
|
134 | Each node represents a file or directory inside the working directory | |
135 | or its parent changeset. |
|
135 | or its parent changeset. | |
136 | This tree has the same structure as the filesystem, |
|
136 | This tree has the same structure as the filesystem, | |
137 | so a node representing a directory has child nodes representing |
|
137 | so a node representing a directory has child nodes representing | |
138 | the files and subdirectories contained directly in that directory. |
|
138 | the files and subdirectories contained directly in that directory. | |
139 |
|
139 | |||
140 | The docket file format |
|
140 | The docket file format | |
141 | ---------------------- |
|
141 | ---------------------- | |
142 |
|
142 | |||
143 | This is implemented in `rust/hg-core/src/dirstate_tree/on_disk.rs` |
|
143 | This is implemented in `rust/hg-core/src/dirstate_tree/on_disk.rs` | |
144 | and `mercurial/dirstateutils/docket.py`. |
|
144 | and `mercurial/dirstateutils/docket.py`. | |
145 |
|
145 | |||
146 | Components of the docket file are found at fixed offsets, |
|
146 | Components of the docket file are found at fixed offsets, | |
147 | counted in bytes from the start of the file: |
|
147 | counted in bytes from the start of the file: | |
148 |
|
148 | |||
149 | * Offset 0: |
|
149 | * Offset 0: | |
150 | The 12-bytes marker string "dirstate-v2\n" ending with a newline character. |
|
150 | The 12-bytes marker string "dirstate-v2\n" ending with a newline character. | |
151 | This makes it easier to tell a dirstate-v2 file from a dirstate-v1 file, |
|
151 | This makes it easier to tell a dirstate-v2 file from a dirstate-v1 file, | |
152 | although it is not strictly necessary |
|
152 | although it is not strictly necessary | |
153 | since `.hg/requires` determines which format to use. |
|
153 | since `.hg/requires` determines which format to use. | |
154 |
|
154 | |||
155 | * Offset 12: |
|
155 | * Offset 12: | |
156 | The changeset node ID on the first parent of the working directory, |
|
156 | The changeset node ID on the first parent of the working directory, | |
157 | as up to 32 binary bytes. |
|
157 | as up to 32 binary bytes. | |
158 | If a node ID is shorter (20 bytes for SHA-1), |
|
158 | If a node ID is shorter (20 bytes for SHA-1), | |
159 | it is start-aligned and the rest of the bytes are set to zero. |
|
159 | it is start-aligned and the rest of the bytes are set to zero. | |
160 |
|
160 | |||
161 | * Offset 44: |
|
161 | * Offset 44: | |
162 | The changeset node ID on the second parent of the working directory, |
|
162 | The changeset node ID on the second parent of the working directory, | |
163 | or all zeros if there isnβt one. |
|
163 | or all zeros if there isnβt one. | |
164 | Also 32 binary bytes. |
|
164 | Also 32 binary bytes. | |
165 |
|
165 | |||
166 | * Offset 76: |
|
166 | * Offset 76: | |
167 | Tree metadata on 44 bytes, described below. |
|
167 | Tree metadata on 44 bytes, described below. | |
168 | Its separation in this documentation from the rest of the docket |
|
168 | Its separation in this documentation from the rest of the docket | |
169 | reflects a detail of the current implementation. |
|
169 | reflects a detail of the current implementation. | |
170 | Since tree metadata is also made of fields at fixed offsets, those could |
|
170 | Since tree metadata is also made of fields at fixed offsets, those could | |
171 | be inlined here by adding 76 bytes to each offset. |
|
171 | be inlined here by adding 76 bytes to each offset. | |
172 |
|
172 | |||
173 | * Offset 120: |
|
173 | * Offset 120: | |
174 | The used size of the data file, as a 32-bit big-endian integer. |
|
174 | The used size of the data file, as a 32-bit big-endian integer. | |
175 | The actual size of the data file may be larger |
|
175 | The actual size of the data file may be larger | |
176 | (if another Mercurial processis in appending to it |
|
176 | (if another Mercurial processis in appending to it | |
177 | but has not updated the docket yet). |
|
177 | but has not updated the docket yet). | |
178 | That extra data must be ignored. |
|
178 | That extra data must be ignored. | |
179 |
|
179 | |||
180 | * Offset 124: |
|
180 | * Offset 124: | |
181 | The length of the data file identifier, as a 8-bit integer. |
|
181 | The length of the data file identifier, as a 8-bit integer. | |
182 |
|
182 | |||
183 | * Offset 125: |
|
183 | * Offset 125: | |
184 | The data file identifier. |
|
184 | The data file identifier. | |
185 |
|
185 | |||
186 | * Any additional data is current ignored, and dropped when updating the file. |
|
186 | * Any additional data is current ignored, and dropped when updating the file. | |
187 |
|
187 | |||
188 | Tree metadata in the docket file |
|
188 | Tree metadata in the docket file | |
189 | -------------------------------- |
|
189 | -------------------------------- | |
190 |
|
190 | |||
191 | Tree metadata is similarly made of components at fixed offsets. |
|
191 | Tree metadata is similarly made of components at fixed offsets. | |
192 | These offsets are counted in bytes from the start of tree metadata, |
|
192 | These offsets are counted in bytes from the start of tree metadata, | |
193 | which is 76 bytes after the start of the docket file. |
|
193 | which is 76 bytes after the start of the docket file. | |
194 |
|
194 | |||
195 | This metadata can be thought of as the singular root of the tree |
|
195 | This metadata can be thought of as the singular root of the tree | |
196 | formed by nodes in the data file. |
|
196 | formed by nodes in the data file. | |
197 |
|
197 | |||
198 | * Offset 0: |
|
198 | * Offset 0: | |
199 | Pseudo-pointer to the start of root nodes, |
|
199 | Pseudo-pointer to the start of root nodes, | |
200 | counted in bytes from the start of the data file, |
|
200 | counted in bytes from the start of the data file, | |
201 | as a 32-bit big-endian integer. |
|
201 | as a 32-bit big-endian integer. | |
202 | These nodes describe files and directories found directly |
|
202 | These nodes describe files and directories found directly | |
203 | at the root of the working directory. |
|
203 | at the root of the working directory. | |
204 |
|
204 | |||
205 | * Offset 4: |
|
205 | * Offset 4: | |
206 | Number of root nodes, as a 32-bit big-endian integer. |
|
206 | Number of root nodes, as a 32-bit big-endian integer. | |
207 |
|
207 | |||
208 | * Offset 8: |
|
208 | * Offset 8: | |
209 | Total number of nodes in the entire tree that "have a dirstate entry", |
|
209 | Total number of nodes in the entire tree that "have a dirstate entry", | |
210 | as a 32-bit big-endian integer. |
|
210 | as a 32-bit big-endian integer. | |
211 | Those nodes represent files that would be present at all in `dirstate-v1`. |
|
211 | Those nodes represent files that would be present at all in `dirstate-v1`. | |
212 | This is typically less than the total number of nodes. |
|
212 | This is typically less than the total number of nodes. | |
213 | This counter is used to implement `len(dirstatemap)`. |
|
213 | This counter is used to implement `len(dirstatemap)`. | |
214 |
|
214 | |||
215 | * Offset 12: |
|
215 | * Offset 12: | |
216 | Number of nodes in the entire tree that have a copy source, |
|
216 | Number of nodes in the entire tree that have a copy source, | |
217 | as a 32-bit big-endian integer. |
|
217 | as a 32-bit big-endian integer. | |
218 | At the next commit, these files are recorded |
|
218 | At the next commit, these files are recorded | |
219 | as having been copied or moved/renamed from that source. |
|
219 | as having been copied or moved/renamed from that source. | |
220 | (A move is recorded as a copy and separate removal of the source.) |
|
220 | (A move is recorded as a copy and separate removal of the source.) | |
221 | This counter is used to implement `len(dirstatemap.copymap)`. |
|
221 | This counter is used to implement `len(dirstatemap.copymap)`. | |
222 |
|
222 | |||
223 | * Offset 16: |
|
223 | * Offset 16: | |
224 | An estimation of how many bytes of the data file |
|
224 | An estimation of how many bytes of the data file | |
225 | (within its used size) are unused, as a 32-bit big-endian integer. |
|
225 | (within its used size) are unused, as a 32-bit big-endian integer. | |
226 | When appending to an existing data file, |
|
226 | When appending to an existing data file, | |
227 | some existing nodes or paths can be unreachable from the new root |
|
227 | some existing nodes or paths can be unreachable from the new root | |
228 | but they still take up space. |
|
228 | but they still take up space. | |
229 | This counter is used to decide when to write a new data file from scratch |
|
229 | This counter is used to decide when to write a new data file from scratch | |
230 | instead of appending to an existing one, |
|
230 | instead of appending to an existing one, | |
231 | in order to get rid of that unreachable data |
|
231 | in order to get rid of that unreachable data | |
232 | and avoid unbounded file size growth. |
|
232 | and avoid unbounded file size growth. | |
233 |
|
233 | |||
234 | * Offset 20: |
|
234 | * Offset 20: | |
235 | These four bytes are currently ignored |
|
235 | These four bytes are currently ignored | |
236 | and reset to zero when updating a docket file. |
|
236 | and reset to zero when updating a docket file. | |
237 | This is an attempt at forward compatibility: |
|
237 | This is an attempt at forward compatibility: | |
238 | future Mercurial versions could use this as a bit field |
|
238 | future Mercurial versions could use this as a bit field | |
239 | to indicate that a dirstate has additional data or constraints. |
|
239 | to indicate that a dirstate has additional data or constraints. | |
240 | Finding a dirstate file with the relevant bit unset indicates that |
|
240 | Finding a dirstate file with the relevant bit unset indicates that | |
241 | it was written by a then-older version |
|
241 | it was written by a then-older version | |
242 | which is not aware of that future change. |
|
242 | which is not aware of that future change. | |
243 |
|
243 | |||
244 | * Offset 24: |
|
244 | * Offset 24: | |
245 | Either 20 zero bytes, or a SHA-1 hash as 20 binary bytes. |
|
245 | Either 20 zero bytes, or a SHA-1 hash as 20 binary bytes. | |
246 | When present, the hash is of ignore patterns |
|
246 | When present, the hash is of ignore patterns | |
247 | that were used for some previous run of the `status` algorithm. |
|
247 | that were used for some previous run of the `status` algorithm. | |
248 |
|
248 | |||
249 | * (Offset 44: end of tree metadata) |
|
249 | * (Offset 44: end of tree metadata) | |
250 |
|
250 | |||
251 | Optional hash of ignore patterns |
|
251 | Optional hash of ignore patterns | |
252 | -------------------------------- |
|
252 | -------------------------------- | |
253 |
|
253 | |||
254 | The implementation of `status` at `rust/hg-core/src/dirstate_tree/status.rs` |
|
254 | The implementation of `status` at `rust/hg-core/src/dirstate_tree/status.rs` | |
255 | has been optimized such that its run time is dominated by calls |
|
255 | has been optimized such that its run time is dominated by calls | |
256 | to `stat` for reading the filesystem metadata of a file or directory, |
|
256 | to `stat` for reading the filesystem metadata of a file or directory, | |
257 | and to `readdir` for listing the contents of a directory. |
|
257 | and to `readdir` for listing the contents of a directory. | |
258 | In some cases the algorithm can skip calls to `readdir` |
|
258 | In some cases the algorithm can skip calls to `readdir` | |
259 | (saving significant time) |
|
259 | (saving significant time) | |
260 | because the dirstate already contains enough of the relevant information |
|
260 | because the dirstate already contains enough of the relevant information | |
261 | to build the correct `status` results. |
|
261 | to build the correct `status` results. | |
262 |
|
262 | |||
263 | The default configuration of `hg status` is to list unknown files |
|
263 | The default configuration of `hg status` is to list unknown files | |
264 | but not ignored files. |
|
264 | but not ignored files. | |
265 | In this case, it matters for the `readdir`-skipping optimization |
|
265 | In this case, it matters for the `readdir`-skipping optimization | |
266 | if a given file used to be ignored but became unknown |
|
266 | if a given file used to be ignored but became unknown | |
267 | because `.hgignore` changed. |
|
267 | because `.hgignore` changed. | |
268 | To detect the possibility of such a change, |
|
268 | To detect the possibility of such a change, | |
269 | the tree metadata contains an optional hash of all ignore patterns. |
|
269 | the tree metadata contains an optional hash of all ignore patterns. | |
270 |
|
270 | |||
271 | We define: |
|
271 | We define: | |
272 |
|
272 | |||
273 | * "Root" ignore files as: |
|
273 | * "Root" ignore files as: | |
274 |
|
274 | |||
275 | - `.hgignore` at the root of the repository if it exists |
|
275 | - `.hgignore` at the root of the repository if it exists | |
276 | - And all files from `ui.ignore.*` config. |
|
276 | - And all files from `ui.ignore.*` config. | |
277 |
|
277 | |||
278 | This set of files is sorted by the string representation of their path. |
|
278 | This set of files is sorted by the string representation of their path. | |
279 |
|
279 | |||
280 | * The "expanded contents" of an ignore files is the byte string made |
|
280 | * The "expanded contents" of an ignore files is the byte string made | |
281 | by the concatenation of its contents followed by the "expanded contents" |
|
281 | by the concatenation of its contents followed by the "expanded contents" | |
282 | of other files included with `include:` or `subinclude:` directives, |
|
282 | of other files included with `include:` or `subinclude:` directives, | |
283 | in inclusion order. This definition is recursive, as included files can |
|
283 | in inclusion order. This definition is recursive, as included files can | |
284 | themselves include more files. |
|
284 | themselves include more files. | |
285 |
|
285 | |||
286 | This hash is defined as the SHA-1 of the concatenation (in sorted |
|
286 | This hash is defined as the SHA-1 of the concatenation (in sorted | |
287 | order) of the "expanded contents" of each "root" ignore file. |
|
287 | order) of the "expanded contents" of each "root" ignore file. | |
288 | (Note that computing this does not require actually concatenating |
|
288 | (Note that computing this does not require actually concatenating | |
289 | into a single contiguous byte sequence. |
|
289 | into a single contiguous byte sequence. | |
290 | Instead a SHA-1 hasher object can be created |
|
290 | Instead a SHA-1 hasher object can be created | |
291 | and fed separate chunks one by one.) |
|
291 | and fed separate chunks one by one.) | |
292 |
|
292 | |||
293 | The data file format |
|
293 | The data file format | |
294 | -------------------- |
|
294 | -------------------- | |
295 |
|
295 | |||
296 | This is implemented in `rust/hg-core/src/dirstate_tree/on_disk.rs` |
|
296 | This is implemented in `rust/hg-core/src/dirstate_tree/on_disk.rs` | |
297 | and `mercurial/dirstateutils/v2.py`. |
|
297 | and `mercurial/dirstateutils/v2.py`. | |
298 |
|
298 | |||
299 | The data file contains two types of data: paths and nodes. |
|
299 | The data file contains two types of data: paths and nodes. | |
300 |
|
300 | |||
301 | Paths and nodes can be organized in any order in the file, except that sibling |
|
301 | Paths and nodes can be organized in any order in the file, except that sibling | |
302 | nodes must be next to each other and sorted by their path. |
|
302 | nodes must be next to each other and sorted by their path. | |
303 | Contiguity lets the parent refer to them all |
|
303 | Contiguity lets the parent refer to them all | |
304 | by their count and a single pseudo-pointer, |
|
304 | by their count and a single pseudo-pointer, | |
305 | instead of storing one pseudo-pointer per child node. |
|
305 | instead of storing one pseudo-pointer per child node. | |
306 | Sorting allows using binary seach to find a child node with a given name |
|
306 | Sorting allows using binary seach to find a child node with a given name | |
307 | in `O(log(n))` byte sequence comparisons. |
|
307 | in `O(log(n))` byte sequence comparisons. | |
308 |
|
308 | |||
309 | The current implemention writes paths and child node before a given node |
|
309 | The current implemention writes paths and child node before a given node | |
310 | for ease of figuring out the value of pseudo-pointers by the time the are to be |
|
310 | for ease of figuring out the value of pseudo-pointers by the time the are to be | |
311 | written, but this is not an obligation and readers must not rely on it. |
|
311 | written, but this is not an obligation and readers must not rely on it. | |
312 |
|
312 | |||
313 | A path is stored as a byte string anywhere in the file, without delimiter. |
|
313 | A path is stored as a byte string anywhere in the file, without delimiter. | |
314 | It is refered to by one or more node by a pseudo-pointer to its start, and its |
|
314 | It is refered to by one or more node by a pseudo-pointer to its start, and its | |
315 | length in bytes. Since there is no delimiter, |
|
315 | length in bytes. Since there is no delimiter, | |
316 | when a path is a substring of another the same bytes could be reused, |
|
316 | when a path is a substring of another the same bytes could be reused, | |
317 | although the implementation does not exploit this as of this writing. |
|
317 | although the implementation does not exploit this as of this writing. | |
318 |
|
318 | |||
319 | A node is stored on 43 bytes with components at fixed offsets. Paths and |
|
319 | A node is stored on 43 bytes with components at fixed offsets. Paths and | |
320 | child nodes relevant to a node are stored externally and referenced though |
|
320 | child nodes relevant to a node are stored externally and referenced though | |
321 | pseudo-pointers. |
|
321 | pseudo-pointers. | |
322 |
|
322 | |||
323 | All integers are stored in big-endian. All pseudo-pointers are 32-bit integers |
|
323 | All integers are stored in big-endian. All pseudo-pointers are 32-bit integers | |
324 | counting bytes from the start of the data file. Path lengths and positions |
|
324 | counting bytes from the start of the data file. Path lengths and positions | |
325 | are 16-bit integers, also counted in bytes. |
|
325 | are 16-bit integers, also counted in bytes. | |
326 |
|
326 | |||
327 | Node components are: |
|
327 | Node components are: | |
328 |
|
328 | |||
329 | * Offset 0: |
|
329 | * Offset 0: | |
330 | Pseudo-pointer to the full path of this node, |
|
330 | Pseudo-pointer to the full path of this node, | |
331 | from the working directory root. |
|
331 | from the working directory root. | |
332 |
|
332 | |||
333 | * Offset 4: |
|
333 | * Offset 4: | |
334 | Length of the full path. |
|
334 | Length of the full path. | |
335 |
|
335 | |||
336 | * Offset 6: |
|
336 | * Offset 6: | |
337 | Position of the last `/` path separator within the full path, |
|
337 | Position of the last `/` path separator within the full path, | |
338 | in bytes from the start of the full path, |
|
338 | in bytes from the start of the full path, | |
339 | or zero if there isnβt one. |
|
339 | or zero if there isnβt one. | |
340 | The part of the full path after this position is the "base name". |
|
340 | The part of the full path after this position is the "base name". | |
341 | Since sibling nodes have the same parent, only their base name vary |
|
341 | Since sibling nodes have the same parent, only their base name vary | |
342 | and needs to be considered when doing binary search to find a given path. |
|
342 | and needs to be considered when doing binary search to find a given path. | |
343 |
|
343 | |||
344 | * Offset 8: |
|
344 | * Offset 8: | |
345 | Pseudo-pointer to the "copy source" path for this node, |
|
345 | Pseudo-pointer to the "copy source" path for this node, | |
346 | or zero if there is no copy source. |
|
346 | or zero if there is no copy source. | |
347 |
|
347 | |||
348 | * Offset 12: |
|
348 | * Offset 12: | |
349 | Length of the copy source path, or zero if there isnβt one. |
|
349 | Length of the copy source path, or zero if there isnβt one. | |
350 |
|
350 | |||
351 | * Offset 14: |
|
351 | * Offset 14: | |
352 | Pseudo-pointer to the start of child nodes. |
|
352 | Pseudo-pointer to the start of child nodes. | |
353 |
|
353 | |||
354 | * Offset 18: |
|
354 | * Offset 18: | |
355 | Number of child nodes, as a 32-bit integer. |
|
355 | Number of child nodes, as a 32-bit integer. | |
356 | They occupy 43 times this number of bytes |
|
356 | They occupy 43 times this number of bytes | |
357 | (not counting space for paths, and further descendants). |
|
357 | (not counting space for paths, and further descendants). | |
358 |
|
358 | |||
359 | * Offset 22: |
|
359 | * Offset 22: | |
360 | Number as a 32-bit integer of descendant nodes in this subtree, |
|
360 | Number as a 32-bit integer of descendant nodes in this subtree, | |
361 | not including this node itself, |
|
361 | not including this node itself, | |
362 | that "have a dirstate entry". |
|
362 | that "have a dirstate entry". | |
363 | Those nodes represent files that would be present at all in `dirstate-v1`. |
|
363 | Those nodes represent files that would be present at all in `dirstate-v1`. | |
364 | This is typically less than the total number of descendants. |
|
364 | This is typically less than the total number of descendants. | |
365 | This counter is used to implement `has_dir`. |
|
365 | This counter is used to implement `has_dir`. | |
366 |
|
366 | |||
367 | * Offset 26: |
|
367 | * Offset 26: | |
368 | Number as a 32-bit integer of descendant nodes in this subtree, |
|
368 | Number as a 32-bit integer of descendant nodes in this subtree, | |
369 | not including this node itself, |
|
369 | not including this node itself, | |
370 | that represent files tracked in the working directory. |
|
370 | that represent files tracked in the working directory. | |
371 | (For example, `hg rm` makes a file untracked.) |
|
371 | (For example, `hg rm` makes a file untracked.) | |
372 | This counter is used to implement `has_tracked_dir`. |
|
372 | This counter is used to implement `has_tracked_dir`. | |
373 |
|
373 | |||
374 | * Offset 30: |
|
374 | * Offset 30: | |
375 | A `flags` fields that packs some boolean values as bits of a 16-bit integer. |
|
375 | A `flags` fields that packs some boolean values as bits of a 16-bit integer. | |
376 | Starting from least-significant, bit masks are:: |
|
376 | Starting from least-significant, bit masks are:: | |
377 |
|
377 | |||
378 | WDIR_TRACKED = 1 << 0 |
|
378 | WDIR_TRACKED = 1 << 0 | |
379 | P1_TRACKED = 1 << 1 |
|
379 | P1_TRACKED = 1 << 1 | |
380 | P2_INFO = 1 << 2 |
|
380 | P2_INFO = 1 << 2 | |
381 | HAS_MODE_AND_SIZE = 1 << 3 |
|
381 | HAS_MODE_AND_SIZE = 1 << 3 | |
382 | HAS_MTIME = 1 << 4 |
|
382 | HAS_FILE_MTIME = 1 << 4 | |
383 |
|
|
383 | HAS_DIRECTORY_MTIME = 1 << 5 | |
384 |
MODE_ |
|
384 | MODE_EXEC_PERM = 1 << 6 | |
|
385 | MODE_IS_SYMLINK = 1 << 7 | |||
385 |
|
386 | |||
386 | The meaning of each bit is described below. |
|
387 | The meaning of each bit is described below. | |
387 |
|
388 | |||
388 | Other bits are unset. |
|
389 | Other bits are unset. | |
389 | They may be assigned meaning if the future, |
|
390 | They may be assigned meaning if the future, | |
390 | with the limitation that Mercurial versions that pre-date such meaning |
|
391 | with the limitation that Mercurial versions that pre-date such meaning | |
391 | will always reset those bits to unset when writing nodes. |
|
392 | will always reset those bits to unset when writing nodes. | |
392 | (A new node is written for any mutation in its subtree, |
|
393 | (A new node is written for any mutation in its subtree, | |
393 | leaving the bytes of the old node unreachable |
|
394 | leaving the bytes of the old node unreachable | |
394 | until the data file is rewritten entirely.) |
|
395 | until the data file is rewritten entirely.) | |
395 |
|
396 | |||
396 | * Offset 32: |
|
397 | * Offset 32: | |
397 | A `size` field described below, as a 32-bit integer. |
|
398 | A `size` field described below, as a 32-bit integer. | |
398 | Unlike in dirstate-v1, negative values are not used. |
|
399 | Unlike in dirstate-v1, negative values are not used. | |
399 |
|
400 | |||
400 | * Offset 36: |
|
401 | * Offset 36: | |
401 | The seconds component of an `mtime` field described below, |
|
402 | The seconds component of an `mtime` field described below, | |
402 | as a 32-bit integer. |
|
403 | as a 32-bit integer. | |
403 | Unlike in dirstate-v1, negative values are not used. |
|
404 | Unlike in dirstate-v1, negative values are not used. | |
|
405 | When `mtime` is used, this is number of seconds since the Unix epoch | |||
|
406 | truncated to its lower 31 bits. | |||
404 |
|
407 | |||
405 | * Offset 40: |
|
408 | * Offset 40: | |
406 | The nanoseconds component of an `mtime` field described below, |
|
409 | The nanoseconds component of an `mtime` field described below, | |
407 | as a 32-bit integer. |
|
410 | as a 32-bit integer. | |
|
411 | When `mtime` is used, | |||
|
412 | this is the number of nanoseconds since `mtime.seconds`, | |||
|
413 | always stritctly less than one billion. | |||
|
414 | ||||
|
415 | This may be zero if more precision is not available. | |||
|
416 | (This can happen because of limitations in any of Mercurial, Python, | |||
|
417 | libc, the operating system, β¦) | |||
|
418 | ||||
|
419 | When comparing two mtimes and either has this component set to zero, | |||
|
420 | the sub-second precision of both should be ignored. | |||
|
421 | False positives when checking mtime equality due to clock resolution | |||
|
422 | are always possible and the status algorithm needs to deal with them, | |||
|
423 | but having too many false negatives could be harmful too. | |||
408 |
|
424 | |||
409 | * (Offset 44: end of this node) |
|
425 | * (Offset 44: end of this node) | |
410 |
|
426 | |||
411 | The meaning of the boolean values packed in `flags` is: |
|
427 | The meaning of the boolean values packed in `flags` is: | |
412 |
|
428 | |||
413 | `WDIR_TRACKED` |
|
429 | `WDIR_TRACKED` | |
414 | Set if the working directory contains a tracked file at this nodeβs path. |
|
430 | Set if the working directory contains a tracked file at this nodeβs path. | |
415 | This is typically set and unset by `hg add` and `hg rm`. |
|
431 | This is typically set and unset by `hg add` and `hg rm`. | |
416 |
|
432 | |||
417 | `P1_TRACKED` |
|
433 | `P1_TRACKED` | |
418 | Set if the working directoryβs first parent changeset |
|
434 | Set if the working directoryβs first parent changeset | |
419 | (whose node identifier is found in tree metadata) |
|
435 | (whose node identifier is found in tree metadata) | |
420 | contains a tracked file at this nodeβs path. |
|
436 | contains a tracked file at this nodeβs path. | |
421 | This is a cache to reduce manifest lookups. |
|
437 | This is a cache to reduce manifest lookups. | |
422 |
|
438 | |||
423 | `P2_INFO` |
|
439 | `P2_INFO` | |
424 | Set if the file has been involved in some merge operation. |
|
440 | Set if the file has been involved in some merge operation. | |
425 | Either because it was actually merged, |
|
441 | Either because it was actually merged, | |
426 | or because the version in the second parent p2 version was ahead, |
|
442 | or because the version in the second parent p2 version was ahead, | |
427 | or because some rename moved it there. |
|
443 | or because some rename moved it there. | |
428 | In either case `hg status` will want it displayed as modified. |
|
444 | In either case `hg status` will want it displayed as modified. | |
429 |
|
445 | |||
430 | Files that would be mentioned at all in the `dirstate-v1` file format |
|
446 | Files that would be mentioned at all in the `dirstate-v1` file format | |
431 | have a node with at least one of the above three bits set in `dirstate-v2`. |
|
447 | have a node with at least one of the above three bits set in `dirstate-v2`. | |
432 | Letβs call these files "tracked anywhere", |
|
448 | Letβs call these files "tracked anywhere", | |
433 | and "untracked" the nodes with all three of these bits unset. |
|
449 | and "untracked" the nodes with all three of these bits unset. | |
434 | Untracked nodes are typically for directories: |
|
450 | Untracked nodes are typically for directories: | |
435 | they hold child nodes and form the tree structure. |
|
451 | they hold child nodes and form the tree structure. | |
436 | Additional untracked nodes may also exist. |
|
452 | Additional untracked nodes may also exist. | |
437 | Although implementations should strive to clean up nodes |
|
453 | Although implementations should strive to clean up nodes | |
438 | that are entirely unused, other untracked nodes may also exist. |
|
454 | that are entirely unused, other untracked nodes may also exist. | |
439 | For example, a future version of Mercurial might in some cases |
|
455 | For example, a future version of Mercurial might in some cases | |
440 | add nodes for untracked files or/and ignored files in the working directory |
|
456 | add nodes for untracked files or/and ignored files in the working directory | |
441 | in order to optimize `hg status` |
|
457 | in order to optimize `hg status` | |
442 | by enabling it to skip `readdir` in more cases. |
|
458 | by enabling it to skip `readdir` in more cases. | |
443 |
|
459 | |||
444 | `HAS_MODE_AND_SIZE` |
|
460 | `HAS_MODE_AND_SIZE` | |
445 | Must be unset for untracked nodes. |
|
461 | Must be unset for untracked nodes. | |
446 | For files tracked anywhere, if this is set: |
|
462 | For files tracked anywhere, if this is set: | |
447 | - The `size` field is the expected file size, |
|
463 | - The `size` field is the expected file size, | |
448 | in bytes truncated its lower to 31 bits, |
|
464 | in bytes truncated its lower to 31 bits, | |
449 | for the file to be clean. |
|
465 | for the file to be clean. | |
450 | - The expected execute permission for the fileβs owner |
|
466 | - The expected execute permission for the fileβs owner | |
451 | is given by `MODE_EXEC_PERM` |
|
467 | is given by `MODE_EXEC_PERM` | |
452 | - The expected file type is given by `MODE_IS_SIMLINK`: |
|
468 | - The expected file type is given by `MODE_IS_SIMLINK`: | |
453 | a symbolic link if set, or a normal file if unset. |
|
469 | a symbolic link if set, or a normal file if unset. | |
454 | If this is unset the expected size, permission, and file type are unknown. |
|
470 | If this is unset the expected size, permission, and file type are unknown. | |
455 | The `size` field is unused (set to zero). |
|
471 | The `size` field is unused (set to zero). | |
456 |
|
472 | |||
457 | `HAS_MTIME` |
|
473 | `HAS_FILE_MTIME` | |
458 | If unset, the `mtime` field is unused (set to zero). |
|
474 | Must be unset for untracked nodes. | |
459 | If set, it contains a timestamp represented as |
|
475 | If this and `HAS_DIRECTORY_MTIME` are both unset, | |
460 | - the number of seconds since the Unix epoch, |
|
476 | the `mtime` field is unused (set to zero). | |
461 | truncated to its lower 31 bits. |
|
477 | If this is set, `mtime` is the modification time | |
462 | - and the number of nanoseconds since `mtime.seconds`, |
|
478 | expected for the file to be considered clean. | |
463 | always stritctly less than one billion. |
|
|||
464 | This may be zero if more precision is not available. |
|
|||
465 | (This can happen because of limitations in any of Mercurial, Python, |
|
|||
466 | libc, the operating system, β¦) |
|
|||
467 |
|
479 | |||
468 | If set for a file tracked anywhere, |
|
480 | `HAS_DIRECTORY_MTIME` | |
469 | `mtime` is the expected modification time for the file to be clean. |
|
481 | Must be unset for file tracked anywhere. | |
470 |
|
482 | If this and `HAS_DIRECTORY_MTIME` are both unset, | ||
471 | If set for an untracked node, at some point, |
|
483 | the `mtime` field is unused (set to zero). | |
|
484 | If this is set, at some point, | |||
472 | this path in the working directory was observed: |
|
485 | this path in the working directory was observed: | |
473 |
|
486 | |||
474 | - To be a directory |
|
487 | - To be a directory | |
475 | - With the modification time given in `mtime` |
|
488 | - With the modification time given in `mtime` | |
476 | - That time was already strictly in the past when observed, |
|
489 | - That time was already strictly in the past when observed, | |
477 | meaning that later changes cannot happen in the same clock tick |
|
490 | meaning that later changes cannot happen in the same clock tick | |
478 | and must cause a different modification time |
|
491 | and must cause a different modification time | |
479 | (unless the system clock jumps back and we get unlucky, |
|
492 | (unless the system clock jumps back and we get unlucky, | |
480 | which is not impossible but deemed unlikely enough). |
|
493 | which is not impossible but deemed unlikely enough). | |
481 | - All direct children of this directory |
|
494 | - All direct children of this directory | |
482 | (as returned by `std::fs::read_dir`) |
|
495 | (as returned by `std::fs::read_dir`) | |
483 | either have a corresponding dirstate node, |
|
496 | either have a corresponding dirstate node, | |
484 | or are ignored by ignore patterns whose hash is in tree metadata. |
|
497 | or are ignored by ignore patterns whose hash is in tree metadata. | |
485 |
|
498 | |||
486 | This means that if `std::fs::symlink_metadata` later reports |
|
499 | This means that if `std::fs::symlink_metadata` later reports | |
487 | the same modification time |
|
500 | the same modification time | |
488 | and ignored patterns havenβt changed, |
|
501 | and ignored patterns havenβt changed, | |
489 | a run of status that is not listing ignored files |
|
502 | a run of status that is not listing ignored files | |
490 | can skip calling `std::fs::read_dir` again for this directory, |
|
503 | can skip calling `std::fs::read_dir` again for this directory, | |
491 | and iterate child dirstate nodes instead. |
|
504 | and iterate child dirstate nodes instead. | |
492 |
|
505 | |||
493 | `MODE_EXEC_PERM` |
|
506 | `MODE_EXEC_PERM` | |
494 | Must be unset if `HAS_MODE_AND_SIZE` is unset. |
|
507 | Must be unset if `HAS_MODE_AND_SIZE` is unset. | |
495 | If `HAS_MODE_AND_SIZE` is set, |
|
508 | If `HAS_MODE_AND_SIZE` is set, | |
496 | this indicates whether the fileβs own is expected |
|
509 | this indicates whether the fileβs own is expected | |
497 | to have execute permission. |
|
510 | to have execute permission. | |
498 |
|
511 | |||
499 | `MODE_IS_SYMLINK` |
|
512 | `MODE_IS_SYMLINK` | |
500 | Must be unset if `HAS_MODE_AND_SIZE` is unset. |
|
513 | Must be unset if `HAS_MODE_AND_SIZE` is unset. | |
501 | If `HAS_MODE_AND_SIZE` is set, |
|
514 | If `HAS_MODE_AND_SIZE` is set, | |
502 | this indicates whether the file is expected to be a symlink |
|
515 | this indicates whether the file is expected to be a symlink | |
503 | as opposed to a normal file. |
|
516 | as opposed to a normal file. |
@@ -1,789 +1,790 b'' | |||||
1 | # parsers.py - Python implementation of parsers.c |
|
1 | # parsers.py - Python implementation of parsers.c | |
2 | # |
|
2 | # | |
3 | # Copyright 2009 Olivia Mackall <olivia@selenic.com> and others |
|
3 | # Copyright 2009 Olivia Mackall <olivia@selenic.com> and others | |
4 | # |
|
4 | # | |
5 | # This software may be used and distributed according to the terms of the |
|
5 | # This software may be used and distributed according to the terms of the | |
6 | # GNU General Public License version 2 or any later version. |
|
6 | # GNU General Public License version 2 or any later version. | |
7 |
|
7 | |||
8 | from __future__ import absolute_import |
|
8 | from __future__ import absolute_import | |
9 |
|
9 | |||
10 | import stat |
|
10 | import stat | |
11 | import struct |
|
11 | import struct | |
12 | import zlib |
|
12 | import zlib | |
13 |
|
13 | |||
14 | from ..node import ( |
|
14 | from ..node import ( | |
15 | nullrev, |
|
15 | nullrev, | |
16 | sha1nodeconstants, |
|
16 | sha1nodeconstants, | |
17 | ) |
|
17 | ) | |
18 | from ..thirdparty import attr |
|
18 | from ..thirdparty import attr | |
19 | from .. import ( |
|
19 | from .. import ( | |
20 | error, |
|
20 | error, | |
21 | pycompat, |
|
21 | pycompat, | |
22 | revlogutils, |
|
22 | revlogutils, | |
23 | util, |
|
23 | util, | |
24 | ) |
|
24 | ) | |
25 |
|
25 | |||
26 | from ..revlogutils import nodemap as nodemaputil |
|
26 | from ..revlogutils import nodemap as nodemaputil | |
27 | from ..revlogutils import constants as revlog_constants |
|
27 | from ..revlogutils import constants as revlog_constants | |
28 |
|
28 | |||
29 | stringio = pycompat.bytesio |
|
29 | stringio = pycompat.bytesio | |
30 |
|
30 | |||
31 |
|
31 | |||
32 | _pack = struct.pack |
|
32 | _pack = struct.pack | |
33 | _unpack = struct.unpack |
|
33 | _unpack = struct.unpack | |
34 | _compress = zlib.compress |
|
34 | _compress = zlib.compress | |
35 | _decompress = zlib.decompress |
|
35 | _decompress = zlib.decompress | |
36 |
|
36 | |||
37 |
|
37 | |||
38 | # a special value used internally for `size` if the file come from the other parent |
|
38 | # a special value used internally for `size` if the file come from the other parent | |
39 | FROM_P2 = -2 |
|
39 | FROM_P2 = -2 | |
40 |
|
40 | |||
41 | # a special value used internally for `size` if the file is modified/merged/added |
|
41 | # a special value used internally for `size` if the file is modified/merged/added | |
42 | NONNORMAL = -1 |
|
42 | NONNORMAL = -1 | |
43 |
|
43 | |||
44 | # a special value used internally for `time` if the time is ambigeous |
|
44 | # a special value used internally for `time` if the time is ambigeous | |
45 | AMBIGUOUS_TIME = -1 |
|
45 | AMBIGUOUS_TIME = -1 | |
46 |
|
46 | |||
47 | # Bits of the `flags` byte inside a node in the file format |
|
47 | # Bits of the `flags` byte inside a node in the file format | |
48 | DIRSTATE_V2_WDIR_TRACKED = 1 << 0 |
|
48 | DIRSTATE_V2_WDIR_TRACKED = 1 << 0 | |
49 | DIRSTATE_V2_P1_TRACKED = 1 << 1 |
|
49 | DIRSTATE_V2_P1_TRACKED = 1 << 1 | |
50 | DIRSTATE_V2_P2_INFO = 1 << 2 |
|
50 | DIRSTATE_V2_P2_INFO = 1 << 2 | |
51 | DIRSTATE_V2_HAS_MODE_AND_SIZE = 1 << 3 |
|
51 | DIRSTATE_V2_HAS_MODE_AND_SIZE = 1 << 3 | |
52 | DIRSTATE_V2_HAS_MTIME = 1 << 4 |
|
52 | DIRSTATE_V2_HAS_FILE_MTIME = 1 << 4 | |
53 | DIRSTATE_V2_MODE_EXEC_PERM = 1 << 5 |
|
53 | _DIRSTATE_V2_HAS_DIRCTORY_MTIME = 1 << 5 # Unused when Rust is not available | |
54 |
DIRSTATE_V2_MODE_ |
|
54 | DIRSTATE_V2_MODE_EXEC_PERM = 1 << 6 | |
|
55 | DIRSTATE_V2_MODE_IS_SYMLINK = 1 << 7 | |||
55 |
|
56 | |||
56 |
|
57 | |||
57 | @attr.s(slots=True, init=False) |
|
58 | @attr.s(slots=True, init=False) | |
58 | class DirstateItem(object): |
|
59 | class DirstateItem(object): | |
59 | """represent a dirstate entry |
|
60 | """represent a dirstate entry | |
60 |
|
61 | |||
61 | It hold multiple attributes |
|
62 | It hold multiple attributes | |
62 |
|
63 | |||
63 | # about file tracking |
|
64 | # about file tracking | |
64 | - wc_tracked: is the file tracked by the working copy |
|
65 | - wc_tracked: is the file tracked by the working copy | |
65 | - p1_tracked: is the file tracked in working copy first parent |
|
66 | - p1_tracked: is the file tracked in working copy first parent | |
66 | - p2_info: the file has been involved in some merge operation. Either |
|
67 | - p2_info: the file has been involved in some merge operation. Either | |
67 | because it was actually merged, or because the p2 version was |
|
68 | because it was actually merged, or because the p2 version was | |
68 | ahead, or because some rename moved it there. In either case |
|
69 | ahead, or because some rename moved it there. In either case | |
69 | `hg status` will want it displayed as modified. |
|
70 | `hg status` will want it displayed as modified. | |
70 |
|
71 | |||
71 | # about the file state expected from p1 manifest: |
|
72 | # about the file state expected from p1 manifest: | |
72 | - mode: the file mode in p1 |
|
73 | - mode: the file mode in p1 | |
73 | - size: the file size in p1 |
|
74 | - size: the file size in p1 | |
74 |
|
75 | |||
75 | These value can be set to None, which mean we don't have a meaningful value |
|
76 | These value can be set to None, which mean we don't have a meaningful value | |
76 | to compare with. Either because we don't really care about them as there |
|
77 | to compare with. Either because we don't really care about them as there | |
77 | `status` is known without having to look at the disk or because we don't |
|
78 | `status` is known without having to look at the disk or because we don't | |
78 | know these right now and a full comparison will be needed to find out if |
|
79 | know these right now and a full comparison will be needed to find out if | |
79 | the file is clean. |
|
80 | the file is clean. | |
80 |
|
81 | |||
81 | # about the file state on disk last time we saw it: |
|
82 | # about the file state on disk last time we saw it: | |
82 | - mtime: the last known clean mtime for the file. |
|
83 | - mtime: the last known clean mtime for the file. | |
83 |
|
84 | |||
84 | This value can be set to None if no cachable state exist. Either because we |
|
85 | This value can be set to None if no cachable state exist. Either because we | |
85 | do not care (see previous section) or because we could not cache something |
|
86 | do not care (see previous section) or because we could not cache something | |
86 | yet. |
|
87 | yet. | |
87 | """ |
|
88 | """ | |
88 |
|
89 | |||
89 | _wc_tracked = attr.ib() |
|
90 | _wc_tracked = attr.ib() | |
90 | _p1_tracked = attr.ib() |
|
91 | _p1_tracked = attr.ib() | |
91 | _p2_info = attr.ib() |
|
92 | _p2_info = attr.ib() | |
92 | _mode = attr.ib() |
|
93 | _mode = attr.ib() | |
93 | _size = attr.ib() |
|
94 | _size = attr.ib() | |
94 | _mtime = attr.ib() |
|
95 | _mtime = attr.ib() | |
95 |
|
96 | |||
96 | def __init__( |
|
97 | def __init__( | |
97 | self, |
|
98 | self, | |
98 | wc_tracked=False, |
|
99 | wc_tracked=False, | |
99 | p1_tracked=False, |
|
100 | p1_tracked=False, | |
100 | p2_info=False, |
|
101 | p2_info=False, | |
101 | has_meaningful_data=True, |
|
102 | has_meaningful_data=True, | |
102 | has_meaningful_mtime=True, |
|
103 | has_meaningful_mtime=True, | |
103 | parentfiledata=None, |
|
104 | parentfiledata=None, | |
104 | ): |
|
105 | ): | |
105 | self._wc_tracked = wc_tracked |
|
106 | self._wc_tracked = wc_tracked | |
106 | self._p1_tracked = p1_tracked |
|
107 | self._p1_tracked = p1_tracked | |
107 | self._p2_info = p2_info |
|
108 | self._p2_info = p2_info | |
108 |
|
109 | |||
109 | self._mode = None |
|
110 | self._mode = None | |
110 | self._size = None |
|
111 | self._size = None | |
111 | self._mtime = None |
|
112 | self._mtime = None | |
112 | if parentfiledata is None: |
|
113 | if parentfiledata is None: | |
113 | has_meaningful_mtime = False |
|
114 | has_meaningful_mtime = False | |
114 | has_meaningful_data = False |
|
115 | has_meaningful_data = False | |
115 | if has_meaningful_data: |
|
116 | if has_meaningful_data: | |
116 | self._mode = parentfiledata[0] |
|
117 | self._mode = parentfiledata[0] | |
117 | self._size = parentfiledata[1] |
|
118 | self._size = parentfiledata[1] | |
118 | if has_meaningful_mtime: |
|
119 | if has_meaningful_mtime: | |
119 | self._mtime = parentfiledata[2] |
|
120 | self._mtime = parentfiledata[2] | |
120 |
|
121 | |||
121 | @classmethod |
|
122 | @classmethod | |
122 | def from_v2_data(cls, flags, size, mtime): |
|
123 | def from_v2_data(cls, flags, size, mtime): | |
123 | """Build a new DirstateItem object from V2 data""" |
|
124 | """Build a new DirstateItem object from V2 data""" | |
124 | has_mode_size = bool(flags & DIRSTATE_V2_HAS_MODE_AND_SIZE) |
|
125 | has_mode_size = bool(flags & DIRSTATE_V2_HAS_MODE_AND_SIZE) | |
125 | mode = None |
|
126 | mode = None | |
126 | if has_mode_size: |
|
127 | if has_mode_size: | |
127 | assert stat.S_IXUSR == 0o100 |
|
128 | assert stat.S_IXUSR == 0o100 | |
128 | if flags & DIRSTATE_V2_MODE_EXEC_PERM: |
|
129 | if flags & DIRSTATE_V2_MODE_EXEC_PERM: | |
129 | mode = 0o755 |
|
130 | mode = 0o755 | |
130 | else: |
|
131 | else: | |
131 | mode = 0o644 |
|
132 | mode = 0o644 | |
132 | if flags & DIRSTATE_V2_MODE_IS_SYMLINK: |
|
133 | if flags & DIRSTATE_V2_MODE_IS_SYMLINK: | |
133 | mode |= stat.S_IFLNK |
|
134 | mode |= stat.S_IFLNK | |
134 | else: |
|
135 | else: | |
135 | mode |= stat.S_IFREG |
|
136 | mode |= stat.S_IFREG | |
136 | return cls( |
|
137 | return cls( | |
137 | wc_tracked=bool(flags & DIRSTATE_V2_WDIR_TRACKED), |
|
138 | wc_tracked=bool(flags & DIRSTATE_V2_WDIR_TRACKED), | |
138 | p1_tracked=bool(flags & DIRSTATE_V2_P1_TRACKED), |
|
139 | p1_tracked=bool(flags & DIRSTATE_V2_P1_TRACKED), | |
139 | p2_info=bool(flags & DIRSTATE_V2_P2_INFO), |
|
140 | p2_info=bool(flags & DIRSTATE_V2_P2_INFO), | |
140 | has_meaningful_data=has_mode_size, |
|
141 | has_meaningful_data=has_mode_size, | |
141 | has_meaningful_mtime=bool(flags & DIRSTATE_V2_HAS_MTIME), |
|
142 | has_meaningful_mtime=bool(flags & DIRSTATE_V2_HAS_FILE_MTIME), | |
142 | parentfiledata=(mode, size, mtime), |
|
143 | parentfiledata=(mode, size, mtime), | |
143 | ) |
|
144 | ) | |
144 |
|
145 | |||
145 | @classmethod |
|
146 | @classmethod | |
146 | def from_v1_data(cls, state, mode, size, mtime): |
|
147 | def from_v1_data(cls, state, mode, size, mtime): | |
147 | """Build a new DirstateItem object from V1 data |
|
148 | """Build a new DirstateItem object from V1 data | |
148 |
|
149 | |||
149 | Since the dirstate-v1 format is frozen, the signature of this function |
|
150 | Since the dirstate-v1 format is frozen, the signature of this function | |
150 | is not expected to change, unlike the __init__ one. |
|
151 | is not expected to change, unlike the __init__ one. | |
151 | """ |
|
152 | """ | |
152 | if state == b'm': |
|
153 | if state == b'm': | |
153 | return cls(wc_tracked=True, p1_tracked=True, p2_info=True) |
|
154 | return cls(wc_tracked=True, p1_tracked=True, p2_info=True) | |
154 | elif state == b'a': |
|
155 | elif state == b'a': | |
155 | return cls(wc_tracked=True) |
|
156 | return cls(wc_tracked=True) | |
156 | elif state == b'r': |
|
157 | elif state == b'r': | |
157 | if size == NONNORMAL: |
|
158 | if size == NONNORMAL: | |
158 | p1_tracked = True |
|
159 | p1_tracked = True | |
159 | p2_info = True |
|
160 | p2_info = True | |
160 | elif size == FROM_P2: |
|
161 | elif size == FROM_P2: | |
161 | p1_tracked = False |
|
162 | p1_tracked = False | |
162 | p2_info = True |
|
163 | p2_info = True | |
163 | else: |
|
164 | else: | |
164 | p1_tracked = True |
|
165 | p1_tracked = True | |
165 | p2_info = False |
|
166 | p2_info = False | |
166 | return cls(p1_tracked=p1_tracked, p2_info=p2_info) |
|
167 | return cls(p1_tracked=p1_tracked, p2_info=p2_info) | |
167 | elif state == b'n': |
|
168 | elif state == b'n': | |
168 | if size == FROM_P2: |
|
169 | if size == FROM_P2: | |
169 | return cls(wc_tracked=True, p2_info=True) |
|
170 | return cls(wc_tracked=True, p2_info=True) | |
170 | elif size == NONNORMAL: |
|
171 | elif size == NONNORMAL: | |
171 | return cls(wc_tracked=True, p1_tracked=True) |
|
172 | return cls(wc_tracked=True, p1_tracked=True) | |
172 | elif mtime == AMBIGUOUS_TIME: |
|
173 | elif mtime == AMBIGUOUS_TIME: | |
173 | return cls( |
|
174 | return cls( | |
174 | wc_tracked=True, |
|
175 | wc_tracked=True, | |
175 | p1_tracked=True, |
|
176 | p1_tracked=True, | |
176 | has_meaningful_mtime=False, |
|
177 | has_meaningful_mtime=False, | |
177 | parentfiledata=(mode, size, 42), |
|
178 | parentfiledata=(mode, size, 42), | |
178 | ) |
|
179 | ) | |
179 | else: |
|
180 | else: | |
180 | return cls( |
|
181 | return cls( | |
181 | wc_tracked=True, |
|
182 | wc_tracked=True, | |
182 | p1_tracked=True, |
|
183 | p1_tracked=True, | |
183 | parentfiledata=(mode, size, mtime), |
|
184 | parentfiledata=(mode, size, mtime), | |
184 | ) |
|
185 | ) | |
185 | else: |
|
186 | else: | |
186 | raise RuntimeError(b'unknown state: %s' % state) |
|
187 | raise RuntimeError(b'unknown state: %s' % state) | |
187 |
|
188 | |||
188 | def set_possibly_dirty(self): |
|
189 | def set_possibly_dirty(self): | |
189 | """Mark a file as "possibly dirty" |
|
190 | """Mark a file as "possibly dirty" | |
190 |
|
191 | |||
191 | This means the next status call will have to actually check its content |
|
192 | This means the next status call will have to actually check its content | |
192 | to make sure it is correct. |
|
193 | to make sure it is correct. | |
193 | """ |
|
194 | """ | |
194 | self._mtime = None |
|
195 | self._mtime = None | |
195 |
|
196 | |||
196 | def set_clean(self, mode, size, mtime): |
|
197 | def set_clean(self, mode, size, mtime): | |
197 | """mark a file as "clean" cancelling potential "possibly dirty call" |
|
198 | """mark a file as "clean" cancelling potential "possibly dirty call" | |
198 |
|
199 | |||
199 | Note: this function is a descendant of `dirstate.normal` and is |
|
200 | Note: this function is a descendant of `dirstate.normal` and is | |
200 | currently expected to be call on "normal" entry only. There are not |
|
201 | currently expected to be call on "normal" entry only. There are not | |
201 | reason for this to not change in the future as long as the ccode is |
|
202 | reason for this to not change in the future as long as the ccode is | |
202 | updated to preserve the proper state of the non-normal files. |
|
203 | updated to preserve the proper state of the non-normal files. | |
203 | """ |
|
204 | """ | |
204 | self._wc_tracked = True |
|
205 | self._wc_tracked = True | |
205 | self._p1_tracked = True |
|
206 | self._p1_tracked = True | |
206 | self._mode = mode |
|
207 | self._mode = mode | |
207 | self._size = size |
|
208 | self._size = size | |
208 | self._mtime = mtime |
|
209 | self._mtime = mtime | |
209 |
|
210 | |||
210 | def set_tracked(self): |
|
211 | def set_tracked(self): | |
211 | """mark a file as tracked in the working copy |
|
212 | """mark a file as tracked in the working copy | |
212 |
|
213 | |||
213 | This will ultimately be called by command like `hg add`. |
|
214 | This will ultimately be called by command like `hg add`. | |
214 | """ |
|
215 | """ | |
215 | self._wc_tracked = True |
|
216 | self._wc_tracked = True | |
216 | # `set_tracked` is replacing various `normallookup` call. So we mark |
|
217 | # `set_tracked` is replacing various `normallookup` call. So we mark | |
217 | # the files as needing lookup |
|
218 | # the files as needing lookup | |
218 | # |
|
219 | # | |
219 | # Consider dropping this in the future in favor of something less broad. |
|
220 | # Consider dropping this in the future in favor of something less broad. | |
220 | self._mtime = None |
|
221 | self._mtime = None | |
221 |
|
222 | |||
222 | def set_untracked(self): |
|
223 | def set_untracked(self): | |
223 | """mark a file as untracked in the working copy |
|
224 | """mark a file as untracked in the working copy | |
224 |
|
225 | |||
225 | This will ultimately be called by command like `hg remove`. |
|
226 | This will ultimately be called by command like `hg remove`. | |
226 | """ |
|
227 | """ | |
227 | self._wc_tracked = False |
|
228 | self._wc_tracked = False | |
228 | self._mode = None |
|
229 | self._mode = None | |
229 | self._size = None |
|
230 | self._size = None | |
230 | self._mtime = None |
|
231 | self._mtime = None | |
231 |
|
232 | |||
232 | def drop_merge_data(self): |
|
233 | def drop_merge_data(self): | |
233 | """remove all "merge-only" from a DirstateItem |
|
234 | """remove all "merge-only" from a DirstateItem | |
234 |
|
235 | |||
235 | This is to be call by the dirstatemap code when the second parent is dropped |
|
236 | This is to be call by the dirstatemap code when the second parent is dropped | |
236 | """ |
|
237 | """ | |
237 | if self._p2_info: |
|
238 | if self._p2_info: | |
238 | self._p2_info = False |
|
239 | self._p2_info = False | |
239 | self._mode = None |
|
240 | self._mode = None | |
240 | self._size = None |
|
241 | self._size = None | |
241 | self._mtime = None |
|
242 | self._mtime = None | |
242 |
|
243 | |||
243 | @property |
|
244 | @property | |
244 | def mode(self): |
|
245 | def mode(self): | |
245 | return self.v1_mode() |
|
246 | return self.v1_mode() | |
246 |
|
247 | |||
247 | @property |
|
248 | @property | |
248 | def size(self): |
|
249 | def size(self): | |
249 | return self.v1_size() |
|
250 | return self.v1_size() | |
250 |
|
251 | |||
251 | @property |
|
252 | @property | |
252 | def mtime(self): |
|
253 | def mtime(self): | |
253 | return self.v1_mtime() |
|
254 | return self.v1_mtime() | |
254 |
|
255 | |||
255 | @property |
|
256 | @property | |
256 | def state(self): |
|
257 | def state(self): | |
257 | """ |
|
258 | """ | |
258 | States are: |
|
259 | States are: | |
259 | n normal |
|
260 | n normal | |
260 | m needs merging |
|
261 | m needs merging | |
261 | r marked for removal |
|
262 | r marked for removal | |
262 | a marked for addition |
|
263 | a marked for addition | |
263 |
|
264 | |||
264 | XXX This "state" is a bit obscure and mostly a direct expression of the |
|
265 | XXX This "state" is a bit obscure and mostly a direct expression of the | |
265 | dirstatev1 format. It would make sense to ultimately deprecate it in |
|
266 | dirstatev1 format. It would make sense to ultimately deprecate it in | |
266 | favor of the more "semantic" attributes. |
|
267 | favor of the more "semantic" attributes. | |
267 | """ |
|
268 | """ | |
268 | if not self.any_tracked: |
|
269 | if not self.any_tracked: | |
269 | return b'?' |
|
270 | return b'?' | |
270 | return self.v1_state() |
|
271 | return self.v1_state() | |
271 |
|
272 | |||
272 | @property |
|
273 | @property | |
273 | def tracked(self): |
|
274 | def tracked(self): | |
274 | """True is the file is tracked in the working copy""" |
|
275 | """True is the file is tracked in the working copy""" | |
275 | return self._wc_tracked |
|
276 | return self._wc_tracked | |
276 |
|
277 | |||
277 | @property |
|
278 | @property | |
278 | def any_tracked(self): |
|
279 | def any_tracked(self): | |
279 | """True is the file is tracked anywhere (wc or parents)""" |
|
280 | """True is the file is tracked anywhere (wc or parents)""" | |
280 | return self._wc_tracked or self._p1_tracked or self._p2_info |
|
281 | return self._wc_tracked or self._p1_tracked or self._p2_info | |
281 |
|
282 | |||
282 | @property |
|
283 | @property | |
283 | def added(self): |
|
284 | def added(self): | |
284 | """True if the file has been added""" |
|
285 | """True if the file has been added""" | |
285 | return self._wc_tracked and not (self._p1_tracked or self._p2_info) |
|
286 | return self._wc_tracked and not (self._p1_tracked or self._p2_info) | |
286 |
|
287 | |||
287 | @property |
|
288 | @property | |
288 | def maybe_clean(self): |
|
289 | def maybe_clean(self): | |
289 | """True if the file has a chance to be in the "clean" state""" |
|
290 | """True if the file has a chance to be in the "clean" state""" | |
290 | if not self._wc_tracked: |
|
291 | if not self._wc_tracked: | |
291 | return False |
|
292 | return False | |
292 | elif not self._p1_tracked: |
|
293 | elif not self._p1_tracked: | |
293 | return False |
|
294 | return False | |
294 | elif self._p2_info: |
|
295 | elif self._p2_info: | |
295 | return False |
|
296 | return False | |
296 | return True |
|
297 | return True | |
297 |
|
298 | |||
298 | @property |
|
299 | @property | |
299 | def p1_tracked(self): |
|
300 | def p1_tracked(self): | |
300 | """True if the file is tracked in the first parent manifest""" |
|
301 | """True if the file is tracked in the first parent manifest""" | |
301 | return self._p1_tracked |
|
302 | return self._p1_tracked | |
302 |
|
303 | |||
303 | @property |
|
304 | @property | |
304 | def p2_info(self): |
|
305 | def p2_info(self): | |
305 | """True if the file needed to merge or apply any input from p2 |
|
306 | """True if the file needed to merge or apply any input from p2 | |
306 |
|
307 | |||
307 | See the class documentation for details. |
|
308 | See the class documentation for details. | |
308 | """ |
|
309 | """ | |
309 | return self._wc_tracked and self._p2_info |
|
310 | return self._wc_tracked and self._p2_info | |
310 |
|
311 | |||
311 | @property |
|
312 | @property | |
312 | def removed(self): |
|
313 | def removed(self): | |
313 | """True if the file has been removed""" |
|
314 | """True if the file has been removed""" | |
314 | return not self._wc_tracked and (self._p1_tracked or self._p2_info) |
|
315 | return not self._wc_tracked and (self._p1_tracked or self._p2_info) | |
315 |
|
316 | |||
316 | def v2_data(self): |
|
317 | def v2_data(self): | |
317 | """Returns (flags, mode, size, mtime) for v2 serialization""" |
|
318 | """Returns (flags, mode, size, mtime) for v2 serialization""" | |
318 | flags = 0 |
|
319 | flags = 0 | |
319 | if self._wc_tracked: |
|
320 | if self._wc_tracked: | |
320 | flags |= DIRSTATE_V2_WDIR_TRACKED |
|
321 | flags |= DIRSTATE_V2_WDIR_TRACKED | |
321 | if self._p1_tracked: |
|
322 | if self._p1_tracked: | |
322 | flags |= DIRSTATE_V2_P1_TRACKED |
|
323 | flags |= DIRSTATE_V2_P1_TRACKED | |
323 | if self._p2_info: |
|
324 | if self._p2_info: | |
324 | flags |= DIRSTATE_V2_P2_INFO |
|
325 | flags |= DIRSTATE_V2_P2_INFO | |
325 | if self._mode is not None and self._size is not None: |
|
326 | if self._mode is not None and self._size is not None: | |
326 | flags |= DIRSTATE_V2_HAS_MODE_AND_SIZE |
|
327 | flags |= DIRSTATE_V2_HAS_MODE_AND_SIZE | |
327 | if self.mode & stat.S_IXUSR: |
|
328 | if self.mode & stat.S_IXUSR: | |
328 | flags |= DIRSTATE_V2_MODE_EXEC_PERM |
|
329 | flags |= DIRSTATE_V2_MODE_EXEC_PERM | |
329 | if stat.S_ISLNK(self.mode): |
|
330 | if stat.S_ISLNK(self.mode): | |
330 | flags |= DIRSTATE_V2_MODE_IS_SYMLINK |
|
331 | flags |= DIRSTATE_V2_MODE_IS_SYMLINK | |
331 | if self._mtime is not None: |
|
332 | if self._mtime is not None: | |
332 | flags |= DIRSTATE_V2_HAS_MTIME |
|
333 | flags |= DIRSTATE_V2_HAS_FILE_MTIME | |
333 | return (flags, self._size or 0, self._mtime or 0) |
|
334 | return (flags, self._size or 0, self._mtime or 0) | |
334 |
|
335 | |||
335 | def v1_state(self): |
|
336 | def v1_state(self): | |
336 | """return a "state" suitable for v1 serialization""" |
|
337 | """return a "state" suitable for v1 serialization""" | |
337 | if not self.any_tracked: |
|
338 | if not self.any_tracked: | |
338 | # the object has no state to record, this is -currently- |
|
339 | # the object has no state to record, this is -currently- | |
339 | # unsupported |
|
340 | # unsupported | |
340 | raise RuntimeError('untracked item') |
|
341 | raise RuntimeError('untracked item') | |
341 | elif self.removed: |
|
342 | elif self.removed: | |
342 | return b'r' |
|
343 | return b'r' | |
343 | elif self._p1_tracked and self._p2_info: |
|
344 | elif self._p1_tracked and self._p2_info: | |
344 | return b'm' |
|
345 | return b'm' | |
345 | elif self.added: |
|
346 | elif self.added: | |
346 | return b'a' |
|
347 | return b'a' | |
347 | else: |
|
348 | else: | |
348 | return b'n' |
|
349 | return b'n' | |
349 |
|
350 | |||
350 | def v1_mode(self): |
|
351 | def v1_mode(self): | |
351 | """return a "mode" suitable for v1 serialization""" |
|
352 | """return a "mode" suitable for v1 serialization""" | |
352 | return self._mode if self._mode is not None else 0 |
|
353 | return self._mode if self._mode is not None else 0 | |
353 |
|
354 | |||
354 | def v1_size(self): |
|
355 | def v1_size(self): | |
355 | """return a "size" suitable for v1 serialization""" |
|
356 | """return a "size" suitable for v1 serialization""" | |
356 | if not self.any_tracked: |
|
357 | if not self.any_tracked: | |
357 | # the object has no state to record, this is -currently- |
|
358 | # the object has no state to record, this is -currently- | |
358 | # unsupported |
|
359 | # unsupported | |
359 | raise RuntimeError('untracked item') |
|
360 | raise RuntimeError('untracked item') | |
360 | elif self.removed and self._p1_tracked and self._p2_info: |
|
361 | elif self.removed and self._p1_tracked and self._p2_info: | |
361 | return NONNORMAL |
|
362 | return NONNORMAL | |
362 | elif self._p2_info: |
|
363 | elif self._p2_info: | |
363 | return FROM_P2 |
|
364 | return FROM_P2 | |
364 | elif self.removed: |
|
365 | elif self.removed: | |
365 | return 0 |
|
366 | return 0 | |
366 | elif self.added: |
|
367 | elif self.added: | |
367 | return NONNORMAL |
|
368 | return NONNORMAL | |
368 | elif self._size is None: |
|
369 | elif self._size is None: | |
369 | return NONNORMAL |
|
370 | return NONNORMAL | |
370 | else: |
|
371 | else: | |
371 | return self._size |
|
372 | return self._size | |
372 |
|
373 | |||
373 | def v1_mtime(self): |
|
374 | def v1_mtime(self): | |
374 | """return a "mtime" suitable for v1 serialization""" |
|
375 | """return a "mtime" suitable for v1 serialization""" | |
375 | if not self.any_tracked: |
|
376 | if not self.any_tracked: | |
376 | # the object has no state to record, this is -currently- |
|
377 | # the object has no state to record, this is -currently- | |
377 | # unsupported |
|
378 | # unsupported | |
378 | raise RuntimeError('untracked item') |
|
379 | raise RuntimeError('untracked item') | |
379 | elif self.removed: |
|
380 | elif self.removed: | |
380 | return 0 |
|
381 | return 0 | |
381 | elif self._mtime is None: |
|
382 | elif self._mtime is None: | |
382 | return AMBIGUOUS_TIME |
|
383 | return AMBIGUOUS_TIME | |
383 | elif self._p2_info: |
|
384 | elif self._p2_info: | |
384 | return AMBIGUOUS_TIME |
|
385 | return AMBIGUOUS_TIME | |
385 | elif not self._p1_tracked: |
|
386 | elif not self._p1_tracked: | |
386 | return AMBIGUOUS_TIME |
|
387 | return AMBIGUOUS_TIME | |
387 | else: |
|
388 | else: | |
388 | return self._mtime |
|
389 | return self._mtime | |
389 |
|
390 | |||
390 | def need_delay(self, now): |
|
391 | def need_delay(self, now): | |
391 | """True if the stored mtime would be ambiguous with the current time""" |
|
392 | """True if the stored mtime would be ambiguous with the current time""" | |
392 | return self.v1_state() == b'n' and self.v1_mtime() == now |
|
393 | return self.v1_state() == b'n' and self.v1_mtime() == now | |
393 |
|
394 | |||
394 |
|
395 | |||
395 | def gettype(q): |
|
396 | def gettype(q): | |
396 | return int(q & 0xFFFF) |
|
397 | return int(q & 0xFFFF) | |
397 |
|
398 | |||
398 |
|
399 | |||
399 | class BaseIndexObject(object): |
|
400 | class BaseIndexObject(object): | |
400 | # Can I be passed to an algorithme implemented in Rust ? |
|
401 | # Can I be passed to an algorithme implemented in Rust ? | |
401 | rust_ext_compat = 0 |
|
402 | rust_ext_compat = 0 | |
402 | # Format of an index entry according to Python's `struct` language |
|
403 | # Format of an index entry according to Python's `struct` language | |
403 | index_format = revlog_constants.INDEX_ENTRY_V1 |
|
404 | index_format = revlog_constants.INDEX_ENTRY_V1 | |
404 | # Size of a C unsigned long long int, platform independent |
|
405 | # Size of a C unsigned long long int, platform independent | |
405 | big_int_size = struct.calcsize(b'>Q') |
|
406 | big_int_size = struct.calcsize(b'>Q') | |
406 | # Size of a C long int, platform independent |
|
407 | # Size of a C long int, platform independent | |
407 | int_size = struct.calcsize(b'>i') |
|
408 | int_size = struct.calcsize(b'>i') | |
408 | # An empty index entry, used as a default value to be overridden, or nullrev |
|
409 | # An empty index entry, used as a default value to be overridden, or nullrev | |
409 | null_item = ( |
|
410 | null_item = ( | |
410 | 0, |
|
411 | 0, | |
411 | 0, |
|
412 | 0, | |
412 | 0, |
|
413 | 0, | |
413 | -1, |
|
414 | -1, | |
414 | -1, |
|
415 | -1, | |
415 | -1, |
|
416 | -1, | |
416 | -1, |
|
417 | -1, | |
417 | sha1nodeconstants.nullid, |
|
418 | sha1nodeconstants.nullid, | |
418 | 0, |
|
419 | 0, | |
419 | 0, |
|
420 | 0, | |
420 | revlog_constants.COMP_MODE_INLINE, |
|
421 | revlog_constants.COMP_MODE_INLINE, | |
421 | revlog_constants.COMP_MODE_INLINE, |
|
422 | revlog_constants.COMP_MODE_INLINE, | |
422 | ) |
|
423 | ) | |
423 |
|
424 | |||
424 | @util.propertycache |
|
425 | @util.propertycache | |
425 | def entry_size(self): |
|
426 | def entry_size(self): | |
426 | return self.index_format.size |
|
427 | return self.index_format.size | |
427 |
|
428 | |||
428 | @property |
|
429 | @property | |
429 | def nodemap(self): |
|
430 | def nodemap(self): | |
430 | msg = b"index.nodemap is deprecated, use index.[has_node|rev|get_rev]" |
|
431 | msg = b"index.nodemap is deprecated, use index.[has_node|rev|get_rev]" | |
431 | util.nouideprecwarn(msg, b'5.3', stacklevel=2) |
|
432 | util.nouideprecwarn(msg, b'5.3', stacklevel=2) | |
432 | return self._nodemap |
|
433 | return self._nodemap | |
433 |
|
434 | |||
434 | @util.propertycache |
|
435 | @util.propertycache | |
435 | def _nodemap(self): |
|
436 | def _nodemap(self): | |
436 | nodemap = nodemaputil.NodeMap({sha1nodeconstants.nullid: nullrev}) |
|
437 | nodemap = nodemaputil.NodeMap({sha1nodeconstants.nullid: nullrev}) | |
437 | for r in range(0, len(self)): |
|
438 | for r in range(0, len(self)): | |
438 | n = self[r][7] |
|
439 | n = self[r][7] | |
439 | nodemap[n] = r |
|
440 | nodemap[n] = r | |
440 | return nodemap |
|
441 | return nodemap | |
441 |
|
442 | |||
442 | def has_node(self, node): |
|
443 | def has_node(self, node): | |
443 | """return True if the node exist in the index""" |
|
444 | """return True if the node exist in the index""" | |
444 | return node in self._nodemap |
|
445 | return node in self._nodemap | |
445 |
|
446 | |||
446 | def rev(self, node): |
|
447 | def rev(self, node): | |
447 | """return a revision for a node |
|
448 | """return a revision for a node | |
448 |
|
449 | |||
449 | If the node is unknown, raise a RevlogError""" |
|
450 | If the node is unknown, raise a RevlogError""" | |
450 | return self._nodemap[node] |
|
451 | return self._nodemap[node] | |
451 |
|
452 | |||
452 | def get_rev(self, node): |
|
453 | def get_rev(self, node): | |
453 | """return a revision for a node |
|
454 | """return a revision for a node | |
454 |
|
455 | |||
455 | If the node is unknown, return None""" |
|
456 | If the node is unknown, return None""" | |
456 | return self._nodemap.get(node) |
|
457 | return self._nodemap.get(node) | |
457 |
|
458 | |||
458 | def _stripnodes(self, start): |
|
459 | def _stripnodes(self, start): | |
459 | if '_nodemap' in vars(self): |
|
460 | if '_nodemap' in vars(self): | |
460 | for r in range(start, len(self)): |
|
461 | for r in range(start, len(self)): | |
461 | n = self[r][7] |
|
462 | n = self[r][7] | |
462 | del self._nodemap[n] |
|
463 | del self._nodemap[n] | |
463 |
|
464 | |||
464 | def clearcaches(self): |
|
465 | def clearcaches(self): | |
465 | self.__dict__.pop('_nodemap', None) |
|
466 | self.__dict__.pop('_nodemap', None) | |
466 |
|
467 | |||
467 | def __len__(self): |
|
468 | def __len__(self): | |
468 | return self._lgt + len(self._extra) |
|
469 | return self._lgt + len(self._extra) | |
469 |
|
470 | |||
470 | def append(self, tup): |
|
471 | def append(self, tup): | |
471 | if '_nodemap' in vars(self): |
|
472 | if '_nodemap' in vars(self): | |
472 | self._nodemap[tup[7]] = len(self) |
|
473 | self._nodemap[tup[7]] = len(self) | |
473 | data = self._pack_entry(len(self), tup) |
|
474 | data = self._pack_entry(len(self), tup) | |
474 | self._extra.append(data) |
|
475 | self._extra.append(data) | |
475 |
|
476 | |||
476 | def _pack_entry(self, rev, entry): |
|
477 | def _pack_entry(self, rev, entry): | |
477 | assert entry[8] == 0 |
|
478 | assert entry[8] == 0 | |
478 | assert entry[9] == 0 |
|
479 | assert entry[9] == 0 | |
479 | return self.index_format.pack(*entry[:8]) |
|
480 | return self.index_format.pack(*entry[:8]) | |
480 |
|
481 | |||
481 | def _check_index(self, i): |
|
482 | def _check_index(self, i): | |
482 | if not isinstance(i, int): |
|
483 | if not isinstance(i, int): | |
483 | raise TypeError(b"expecting int indexes") |
|
484 | raise TypeError(b"expecting int indexes") | |
484 | if i < 0 or i >= len(self): |
|
485 | if i < 0 or i >= len(self): | |
485 | raise IndexError |
|
486 | raise IndexError | |
486 |
|
487 | |||
487 | def __getitem__(self, i): |
|
488 | def __getitem__(self, i): | |
488 | if i == -1: |
|
489 | if i == -1: | |
489 | return self.null_item |
|
490 | return self.null_item | |
490 | self._check_index(i) |
|
491 | self._check_index(i) | |
491 | if i >= self._lgt: |
|
492 | if i >= self._lgt: | |
492 | data = self._extra[i - self._lgt] |
|
493 | data = self._extra[i - self._lgt] | |
493 | else: |
|
494 | else: | |
494 | index = self._calculate_index(i) |
|
495 | index = self._calculate_index(i) | |
495 | data = self._data[index : index + self.entry_size] |
|
496 | data = self._data[index : index + self.entry_size] | |
496 | r = self._unpack_entry(i, data) |
|
497 | r = self._unpack_entry(i, data) | |
497 | if self._lgt and i == 0: |
|
498 | if self._lgt and i == 0: | |
498 | offset = revlogutils.offset_type(0, gettype(r[0])) |
|
499 | offset = revlogutils.offset_type(0, gettype(r[0])) | |
499 | r = (offset,) + r[1:] |
|
500 | r = (offset,) + r[1:] | |
500 | return r |
|
501 | return r | |
501 |
|
502 | |||
502 | def _unpack_entry(self, rev, data): |
|
503 | def _unpack_entry(self, rev, data): | |
503 | r = self.index_format.unpack(data) |
|
504 | r = self.index_format.unpack(data) | |
504 | r = r + ( |
|
505 | r = r + ( | |
505 | 0, |
|
506 | 0, | |
506 | 0, |
|
507 | 0, | |
507 | revlog_constants.COMP_MODE_INLINE, |
|
508 | revlog_constants.COMP_MODE_INLINE, | |
508 | revlog_constants.COMP_MODE_INLINE, |
|
509 | revlog_constants.COMP_MODE_INLINE, | |
509 | ) |
|
510 | ) | |
510 | return r |
|
511 | return r | |
511 |
|
512 | |||
512 | def pack_header(self, header): |
|
513 | def pack_header(self, header): | |
513 | """pack header information as binary""" |
|
514 | """pack header information as binary""" | |
514 | v_fmt = revlog_constants.INDEX_HEADER |
|
515 | v_fmt = revlog_constants.INDEX_HEADER | |
515 | return v_fmt.pack(header) |
|
516 | return v_fmt.pack(header) | |
516 |
|
517 | |||
517 | def entry_binary(self, rev): |
|
518 | def entry_binary(self, rev): | |
518 | """return the raw binary string representing a revision""" |
|
519 | """return the raw binary string representing a revision""" | |
519 | entry = self[rev] |
|
520 | entry = self[rev] | |
520 | p = revlog_constants.INDEX_ENTRY_V1.pack(*entry[:8]) |
|
521 | p = revlog_constants.INDEX_ENTRY_V1.pack(*entry[:8]) | |
521 | if rev == 0: |
|
522 | if rev == 0: | |
522 | p = p[revlog_constants.INDEX_HEADER.size :] |
|
523 | p = p[revlog_constants.INDEX_HEADER.size :] | |
523 | return p |
|
524 | return p | |
524 |
|
525 | |||
525 |
|
526 | |||
526 | class IndexObject(BaseIndexObject): |
|
527 | class IndexObject(BaseIndexObject): | |
527 | def __init__(self, data): |
|
528 | def __init__(self, data): | |
528 | assert len(data) % self.entry_size == 0, ( |
|
529 | assert len(data) % self.entry_size == 0, ( | |
529 | len(data), |
|
530 | len(data), | |
530 | self.entry_size, |
|
531 | self.entry_size, | |
531 | len(data) % self.entry_size, |
|
532 | len(data) % self.entry_size, | |
532 | ) |
|
533 | ) | |
533 | self._data = data |
|
534 | self._data = data | |
534 | self._lgt = len(data) // self.entry_size |
|
535 | self._lgt = len(data) // self.entry_size | |
535 | self._extra = [] |
|
536 | self._extra = [] | |
536 |
|
537 | |||
537 | def _calculate_index(self, i): |
|
538 | def _calculate_index(self, i): | |
538 | return i * self.entry_size |
|
539 | return i * self.entry_size | |
539 |
|
540 | |||
540 | def __delitem__(self, i): |
|
541 | def __delitem__(self, i): | |
541 | if not isinstance(i, slice) or not i.stop == -1 or i.step is not None: |
|
542 | if not isinstance(i, slice) or not i.stop == -1 or i.step is not None: | |
542 | raise ValueError(b"deleting slices only supports a:-1 with step 1") |
|
543 | raise ValueError(b"deleting slices only supports a:-1 with step 1") | |
543 | i = i.start |
|
544 | i = i.start | |
544 | self._check_index(i) |
|
545 | self._check_index(i) | |
545 | self._stripnodes(i) |
|
546 | self._stripnodes(i) | |
546 | if i < self._lgt: |
|
547 | if i < self._lgt: | |
547 | self._data = self._data[: i * self.entry_size] |
|
548 | self._data = self._data[: i * self.entry_size] | |
548 | self._lgt = i |
|
549 | self._lgt = i | |
549 | self._extra = [] |
|
550 | self._extra = [] | |
550 | else: |
|
551 | else: | |
551 | self._extra = self._extra[: i - self._lgt] |
|
552 | self._extra = self._extra[: i - self._lgt] | |
552 |
|
553 | |||
553 |
|
554 | |||
554 | class PersistentNodeMapIndexObject(IndexObject): |
|
555 | class PersistentNodeMapIndexObject(IndexObject): | |
555 | """a Debug oriented class to test persistent nodemap |
|
556 | """a Debug oriented class to test persistent nodemap | |
556 |
|
557 | |||
557 | We need a simple python object to test API and higher level behavior. See |
|
558 | We need a simple python object to test API and higher level behavior. See | |
558 | the Rust implementation for more serious usage. This should be used only |
|
559 | the Rust implementation for more serious usage. This should be used only | |
559 | through the dedicated `devel.persistent-nodemap` config. |
|
560 | through the dedicated `devel.persistent-nodemap` config. | |
560 | """ |
|
561 | """ | |
561 |
|
562 | |||
562 | def nodemap_data_all(self): |
|
563 | def nodemap_data_all(self): | |
563 | """Return bytes containing a full serialization of a nodemap |
|
564 | """Return bytes containing a full serialization of a nodemap | |
564 |
|
565 | |||
565 | The nodemap should be valid for the full set of revisions in the |
|
566 | The nodemap should be valid for the full set of revisions in the | |
566 | index.""" |
|
567 | index.""" | |
567 | return nodemaputil.persistent_data(self) |
|
568 | return nodemaputil.persistent_data(self) | |
568 |
|
569 | |||
569 | def nodemap_data_incremental(self): |
|
570 | def nodemap_data_incremental(self): | |
570 | """Return bytes containing a incremental update to persistent nodemap |
|
571 | """Return bytes containing a incremental update to persistent nodemap | |
571 |
|
572 | |||
572 | This containst the data for an append-only update of the data provided |
|
573 | This containst the data for an append-only update of the data provided | |
573 | in the last call to `update_nodemap_data`. |
|
574 | in the last call to `update_nodemap_data`. | |
574 | """ |
|
575 | """ | |
575 | if self._nm_root is None: |
|
576 | if self._nm_root is None: | |
576 | return None |
|
577 | return None | |
577 | docket = self._nm_docket |
|
578 | docket = self._nm_docket | |
578 | changed, data = nodemaputil.update_persistent_data( |
|
579 | changed, data = nodemaputil.update_persistent_data( | |
579 | self, self._nm_root, self._nm_max_idx, self._nm_docket.tip_rev |
|
580 | self, self._nm_root, self._nm_max_idx, self._nm_docket.tip_rev | |
580 | ) |
|
581 | ) | |
581 |
|
582 | |||
582 | self._nm_root = self._nm_max_idx = self._nm_docket = None |
|
583 | self._nm_root = self._nm_max_idx = self._nm_docket = None | |
583 | return docket, changed, data |
|
584 | return docket, changed, data | |
584 |
|
585 | |||
585 | def update_nodemap_data(self, docket, nm_data): |
|
586 | def update_nodemap_data(self, docket, nm_data): | |
586 | """provide full block of persisted binary data for a nodemap |
|
587 | """provide full block of persisted binary data for a nodemap | |
587 |
|
588 | |||
588 | The data are expected to come from disk. See `nodemap_data_all` for a |
|
589 | The data are expected to come from disk. See `nodemap_data_all` for a | |
589 | produceur of such data.""" |
|
590 | produceur of such data.""" | |
590 | if nm_data is not None: |
|
591 | if nm_data is not None: | |
591 | self._nm_root, self._nm_max_idx = nodemaputil.parse_data(nm_data) |
|
592 | self._nm_root, self._nm_max_idx = nodemaputil.parse_data(nm_data) | |
592 | if self._nm_root: |
|
593 | if self._nm_root: | |
593 | self._nm_docket = docket |
|
594 | self._nm_docket = docket | |
594 | else: |
|
595 | else: | |
595 | self._nm_root = self._nm_max_idx = self._nm_docket = None |
|
596 | self._nm_root = self._nm_max_idx = self._nm_docket = None | |
596 |
|
597 | |||
597 |
|
598 | |||
598 | class InlinedIndexObject(BaseIndexObject): |
|
599 | class InlinedIndexObject(BaseIndexObject): | |
599 | def __init__(self, data, inline=0): |
|
600 | def __init__(self, data, inline=0): | |
600 | self._data = data |
|
601 | self._data = data | |
601 | self._lgt = self._inline_scan(None) |
|
602 | self._lgt = self._inline_scan(None) | |
602 | self._inline_scan(self._lgt) |
|
603 | self._inline_scan(self._lgt) | |
603 | self._extra = [] |
|
604 | self._extra = [] | |
604 |
|
605 | |||
605 | def _inline_scan(self, lgt): |
|
606 | def _inline_scan(self, lgt): | |
606 | off = 0 |
|
607 | off = 0 | |
607 | if lgt is not None: |
|
608 | if lgt is not None: | |
608 | self._offsets = [0] * lgt |
|
609 | self._offsets = [0] * lgt | |
609 | count = 0 |
|
610 | count = 0 | |
610 | while off <= len(self._data) - self.entry_size: |
|
611 | while off <= len(self._data) - self.entry_size: | |
611 | start = off + self.big_int_size |
|
612 | start = off + self.big_int_size | |
612 | (s,) = struct.unpack( |
|
613 | (s,) = struct.unpack( | |
613 | b'>i', |
|
614 | b'>i', | |
614 | self._data[start : start + self.int_size], |
|
615 | self._data[start : start + self.int_size], | |
615 | ) |
|
616 | ) | |
616 | if lgt is not None: |
|
617 | if lgt is not None: | |
617 | self._offsets[count] = off |
|
618 | self._offsets[count] = off | |
618 | count += 1 |
|
619 | count += 1 | |
619 | off += self.entry_size + s |
|
620 | off += self.entry_size + s | |
620 | if off != len(self._data): |
|
621 | if off != len(self._data): | |
621 | raise ValueError(b"corrupted data") |
|
622 | raise ValueError(b"corrupted data") | |
622 | return count |
|
623 | return count | |
623 |
|
624 | |||
624 | def __delitem__(self, i): |
|
625 | def __delitem__(self, i): | |
625 | if not isinstance(i, slice) or not i.stop == -1 or i.step is not None: |
|
626 | if not isinstance(i, slice) or not i.stop == -1 or i.step is not None: | |
626 | raise ValueError(b"deleting slices only supports a:-1 with step 1") |
|
627 | raise ValueError(b"deleting slices only supports a:-1 with step 1") | |
627 | i = i.start |
|
628 | i = i.start | |
628 | self._check_index(i) |
|
629 | self._check_index(i) | |
629 | self._stripnodes(i) |
|
630 | self._stripnodes(i) | |
630 | if i < self._lgt: |
|
631 | if i < self._lgt: | |
631 | self._offsets = self._offsets[:i] |
|
632 | self._offsets = self._offsets[:i] | |
632 | self._lgt = i |
|
633 | self._lgt = i | |
633 | self._extra = [] |
|
634 | self._extra = [] | |
634 | else: |
|
635 | else: | |
635 | self._extra = self._extra[: i - self._lgt] |
|
636 | self._extra = self._extra[: i - self._lgt] | |
636 |
|
637 | |||
637 | def _calculate_index(self, i): |
|
638 | def _calculate_index(self, i): | |
638 | return self._offsets[i] |
|
639 | return self._offsets[i] | |
639 |
|
640 | |||
640 |
|
641 | |||
641 | def parse_index2(data, inline, revlogv2=False): |
|
642 | def parse_index2(data, inline, revlogv2=False): | |
642 | if not inline: |
|
643 | if not inline: | |
643 | cls = IndexObject2 if revlogv2 else IndexObject |
|
644 | cls = IndexObject2 if revlogv2 else IndexObject | |
644 | return cls(data), None |
|
645 | return cls(data), None | |
645 | cls = InlinedIndexObject |
|
646 | cls = InlinedIndexObject | |
646 | return cls(data, inline), (0, data) |
|
647 | return cls(data, inline), (0, data) | |
647 |
|
648 | |||
648 |
|
649 | |||
649 | def parse_index_cl_v2(data): |
|
650 | def parse_index_cl_v2(data): | |
650 | return IndexChangelogV2(data), None |
|
651 | return IndexChangelogV2(data), None | |
651 |
|
652 | |||
652 |
|
653 | |||
653 | class IndexObject2(IndexObject): |
|
654 | class IndexObject2(IndexObject): | |
654 | index_format = revlog_constants.INDEX_ENTRY_V2 |
|
655 | index_format = revlog_constants.INDEX_ENTRY_V2 | |
655 |
|
656 | |||
656 | def replace_sidedata_info( |
|
657 | def replace_sidedata_info( | |
657 | self, |
|
658 | self, | |
658 | rev, |
|
659 | rev, | |
659 | sidedata_offset, |
|
660 | sidedata_offset, | |
660 | sidedata_length, |
|
661 | sidedata_length, | |
661 | offset_flags, |
|
662 | offset_flags, | |
662 | compression_mode, |
|
663 | compression_mode, | |
663 | ): |
|
664 | ): | |
664 | """ |
|
665 | """ | |
665 | Replace an existing index entry's sidedata offset and length with new |
|
666 | Replace an existing index entry's sidedata offset and length with new | |
666 | ones. |
|
667 | ones. | |
667 | This cannot be used outside of the context of sidedata rewriting, |
|
668 | This cannot be used outside of the context of sidedata rewriting, | |
668 | inside the transaction that creates the revision `rev`. |
|
669 | inside the transaction that creates the revision `rev`. | |
669 | """ |
|
670 | """ | |
670 | if rev < 0: |
|
671 | if rev < 0: | |
671 | raise KeyError |
|
672 | raise KeyError | |
672 | self._check_index(rev) |
|
673 | self._check_index(rev) | |
673 | if rev < self._lgt: |
|
674 | if rev < self._lgt: | |
674 | msg = b"cannot rewrite entries outside of this transaction" |
|
675 | msg = b"cannot rewrite entries outside of this transaction" | |
675 | raise KeyError(msg) |
|
676 | raise KeyError(msg) | |
676 | else: |
|
677 | else: | |
677 | entry = list(self[rev]) |
|
678 | entry = list(self[rev]) | |
678 | entry[0] = offset_flags |
|
679 | entry[0] = offset_flags | |
679 | entry[8] = sidedata_offset |
|
680 | entry[8] = sidedata_offset | |
680 | entry[9] = sidedata_length |
|
681 | entry[9] = sidedata_length | |
681 | entry[11] = compression_mode |
|
682 | entry[11] = compression_mode | |
682 | entry = tuple(entry) |
|
683 | entry = tuple(entry) | |
683 | new = self._pack_entry(rev, entry) |
|
684 | new = self._pack_entry(rev, entry) | |
684 | self._extra[rev - self._lgt] = new |
|
685 | self._extra[rev - self._lgt] = new | |
685 |
|
686 | |||
686 | def _unpack_entry(self, rev, data): |
|
687 | def _unpack_entry(self, rev, data): | |
687 | data = self.index_format.unpack(data) |
|
688 | data = self.index_format.unpack(data) | |
688 | entry = data[:10] |
|
689 | entry = data[:10] | |
689 | data_comp = data[10] & 3 |
|
690 | data_comp = data[10] & 3 | |
690 | sidedata_comp = (data[10] & (3 << 2)) >> 2 |
|
691 | sidedata_comp = (data[10] & (3 << 2)) >> 2 | |
691 | return entry + (data_comp, sidedata_comp) |
|
692 | return entry + (data_comp, sidedata_comp) | |
692 |
|
693 | |||
693 | def _pack_entry(self, rev, entry): |
|
694 | def _pack_entry(self, rev, entry): | |
694 | data = entry[:10] |
|
695 | data = entry[:10] | |
695 | data_comp = entry[10] & 3 |
|
696 | data_comp = entry[10] & 3 | |
696 | sidedata_comp = (entry[11] & 3) << 2 |
|
697 | sidedata_comp = (entry[11] & 3) << 2 | |
697 | data += (data_comp | sidedata_comp,) |
|
698 | data += (data_comp | sidedata_comp,) | |
698 |
|
699 | |||
699 | return self.index_format.pack(*data) |
|
700 | return self.index_format.pack(*data) | |
700 |
|
701 | |||
701 | def entry_binary(self, rev): |
|
702 | def entry_binary(self, rev): | |
702 | """return the raw binary string representing a revision""" |
|
703 | """return the raw binary string representing a revision""" | |
703 | entry = self[rev] |
|
704 | entry = self[rev] | |
704 | return self._pack_entry(rev, entry) |
|
705 | return self._pack_entry(rev, entry) | |
705 |
|
706 | |||
706 | def pack_header(self, header): |
|
707 | def pack_header(self, header): | |
707 | """pack header information as binary""" |
|
708 | """pack header information as binary""" | |
708 | msg = 'version header should go in the docket, not the index: %d' |
|
709 | msg = 'version header should go in the docket, not the index: %d' | |
709 | msg %= header |
|
710 | msg %= header | |
710 | raise error.ProgrammingError(msg) |
|
711 | raise error.ProgrammingError(msg) | |
711 |
|
712 | |||
712 |
|
713 | |||
713 | class IndexChangelogV2(IndexObject2): |
|
714 | class IndexChangelogV2(IndexObject2): | |
714 | index_format = revlog_constants.INDEX_ENTRY_CL_V2 |
|
715 | index_format = revlog_constants.INDEX_ENTRY_CL_V2 | |
715 |
|
716 | |||
716 | def _unpack_entry(self, rev, data, r=True): |
|
717 | def _unpack_entry(self, rev, data, r=True): | |
717 | items = self.index_format.unpack(data) |
|
718 | items = self.index_format.unpack(data) | |
718 | entry = items[:3] + (rev, rev) + items[3:8] |
|
719 | entry = items[:3] + (rev, rev) + items[3:8] | |
719 | data_comp = items[8] & 3 |
|
720 | data_comp = items[8] & 3 | |
720 | sidedata_comp = (items[8] >> 2) & 3 |
|
721 | sidedata_comp = (items[8] >> 2) & 3 | |
721 | return entry + (data_comp, sidedata_comp) |
|
722 | return entry + (data_comp, sidedata_comp) | |
722 |
|
723 | |||
723 | def _pack_entry(self, rev, entry): |
|
724 | def _pack_entry(self, rev, entry): | |
724 | assert entry[3] == rev, entry[3] |
|
725 | assert entry[3] == rev, entry[3] | |
725 | assert entry[4] == rev, entry[4] |
|
726 | assert entry[4] == rev, entry[4] | |
726 | data = entry[:3] + entry[5:10] |
|
727 | data = entry[:3] + entry[5:10] | |
727 | data_comp = entry[10] & 3 |
|
728 | data_comp = entry[10] & 3 | |
728 | sidedata_comp = (entry[11] & 3) << 2 |
|
729 | sidedata_comp = (entry[11] & 3) << 2 | |
729 | data += (data_comp | sidedata_comp,) |
|
730 | data += (data_comp | sidedata_comp,) | |
730 | return self.index_format.pack(*data) |
|
731 | return self.index_format.pack(*data) | |
731 |
|
732 | |||
732 |
|
733 | |||
733 | def parse_index_devel_nodemap(data, inline): |
|
734 | def parse_index_devel_nodemap(data, inline): | |
734 | """like parse_index2, but alway return a PersistentNodeMapIndexObject""" |
|
735 | """like parse_index2, but alway return a PersistentNodeMapIndexObject""" | |
735 | return PersistentNodeMapIndexObject(data), None |
|
736 | return PersistentNodeMapIndexObject(data), None | |
736 |
|
737 | |||
737 |
|
738 | |||
738 | def parse_dirstate(dmap, copymap, st): |
|
739 | def parse_dirstate(dmap, copymap, st): | |
739 | parents = [st[:20], st[20:40]] |
|
740 | parents = [st[:20], st[20:40]] | |
740 | # dereference fields so they will be local in loop |
|
741 | # dereference fields so they will be local in loop | |
741 | format = b">cllll" |
|
742 | format = b">cllll" | |
742 | e_size = struct.calcsize(format) |
|
743 | e_size = struct.calcsize(format) | |
743 | pos1 = 40 |
|
744 | pos1 = 40 | |
744 | l = len(st) |
|
745 | l = len(st) | |
745 |
|
746 | |||
746 | # the inner loop |
|
747 | # the inner loop | |
747 | while pos1 < l: |
|
748 | while pos1 < l: | |
748 | pos2 = pos1 + e_size |
|
749 | pos2 = pos1 + e_size | |
749 | e = _unpack(b">cllll", st[pos1:pos2]) # a literal here is faster |
|
750 | e = _unpack(b">cllll", st[pos1:pos2]) # a literal here is faster | |
750 | pos1 = pos2 + e[4] |
|
751 | pos1 = pos2 + e[4] | |
751 | f = st[pos2:pos1] |
|
752 | f = st[pos2:pos1] | |
752 | if b'\0' in f: |
|
753 | if b'\0' in f: | |
753 | f, c = f.split(b'\0') |
|
754 | f, c = f.split(b'\0') | |
754 | copymap[f] = c |
|
755 | copymap[f] = c | |
755 | dmap[f] = DirstateItem.from_v1_data(*e[:4]) |
|
756 | dmap[f] = DirstateItem.from_v1_data(*e[:4]) | |
756 | return parents |
|
757 | return parents | |
757 |
|
758 | |||
758 |
|
759 | |||
759 | def pack_dirstate(dmap, copymap, pl, now): |
|
760 | def pack_dirstate(dmap, copymap, pl, now): | |
760 | now = int(now) |
|
761 | now = int(now) | |
761 | cs = stringio() |
|
762 | cs = stringio() | |
762 | write = cs.write |
|
763 | write = cs.write | |
763 | write(b"".join(pl)) |
|
764 | write(b"".join(pl)) | |
764 | for f, e in pycompat.iteritems(dmap): |
|
765 | for f, e in pycompat.iteritems(dmap): | |
765 | if e.need_delay(now): |
|
766 | if e.need_delay(now): | |
766 | # The file was last modified "simultaneously" with the current |
|
767 | # The file was last modified "simultaneously" with the current | |
767 | # write to dirstate (i.e. within the same second for file- |
|
768 | # write to dirstate (i.e. within the same second for file- | |
768 | # systems with a granularity of 1 sec). This commonly happens |
|
769 | # systems with a granularity of 1 sec). This commonly happens | |
769 | # for at least a couple of files on 'update'. |
|
770 | # for at least a couple of files on 'update'. | |
770 | # The user could change the file without changing its size |
|
771 | # The user could change the file without changing its size | |
771 | # within the same second. Invalidate the file's mtime in |
|
772 | # within the same second. Invalidate the file's mtime in | |
772 | # dirstate, forcing future 'status' calls to compare the |
|
773 | # dirstate, forcing future 'status' calls to compare the | |
773 | # contents of the file if the size is the same. This prevents |
|
774 | # contents of the file if the size is the same. This prevents | |
774 | # mistakenly treating such files as clean. |
|
775 | # mistakenly treating such files as clean. | |
775 | e.set_possibly_dirty() |
|
776 | e.set_possibly_dirty() | |
776 |
|
777 | |||
777 | if f in copymap: |
|
778 | if f in copymap: | |
778 | f = b"%s\0%s" % (f, copymap[f]) |
|
779 | f = b"%s\0%s" % (f, copymap[f]) | |
779 | e = _pack( |
|
780 | e = _pack( | |
780 | b">cllll", |
|
781 | b">cllll", | |
781 | e.v1_state(), |
|
782 | e.v1_state(), | |
782 | e.v1_mode(), |
|
783 | e.v1_mode(), | |
783 | e.v1_size(), |
|
784 | e.v1_size(), | |
784 | e.v1_mtime(), |
|
785 | e.v1_mtime(), | |
785 | len(f), |
|
786 | len(f), | |
786 | ) |
|
787 | ) | |
787 | write(e) |
|
788 | write(e) | |
788 | write(f) |
|
789 | write(f) | |
789 | return cs.getvalue() |
|
790 | return cs.getvalue() |
@@ -1,721 +1,726 b'' | |||||
1 | //! The "version 2" disk representation of the dirstate |
|
1 | //! The "version 2" disk representation of the dirstate | |
2 | //! |
|
2 | //! | |
3 | //! See `mercurial/helptext/internals/dirstate-v2.txt` |
|
3 | //! See `mercurial/helptext/internals/dirstate-v2.txt` | |
4 |
|
4 | |||
5 | use crate::dirstate::TruncatedTimestamp; |
|
5 | use crate::dirstate::TruncatedTimestamp; | |
6 | use crate::dirstate_tree::dirstate_map::{self, DirstateMap, NodeRef}; |
|
6 | use crate::dirstate_tree::dirstate_map::{self, DirstateMap, NodeRef}; | |
7 | use crate::dirstate_tree::path_with_basename::WithBasename; |
|
7 | use crate::dirstate_tree::path_with_basename::WithBasename; | |
8 | use crate::errors::HgError; |
|
8 | use crate::errors::HgError; | |
9 | use crate::utils::hg_path::HgPath; |
|
9 | use crate::utils::hg_path::HgPath; | |
10 | use crate::DirstateEntry; |
|
10 | use crate::DirstateEntry; | |
11 | use crate::DirstateError; |
|
11 | use crate::DirstateError; | |
12 | use crate::DirstateParents; |
|
12 | use crate::DirstateParents; | |
13 | use bitflags::bitflags; |
|
13 | use bitflags::bitflags; | |
14 | use bytes_cast::unaligned::{U16Be, U32Be}; |
|
14 | use bytes_cast::unaligned::{U16Be, U32Be}; | |
15 | use bytes_cast::BytesCast; |
|
15 | use bytes_cast::BytesCast; | |
16 | use format_bytes::format_bytes; |
|
16 | use format_bytes::format_bytes; | |
17 | use std::borrow::Cow; |
|
17 | use std::borrow::Cow; | |
18 | use std::convert::{TryFrom, TryInto}; |
|
18 | use std::convert::{TryFrom, TryInto}; | |
19 |
|
19 | |||
20 | /// Added at the start of `.hg/dirstate` when the "v2" format is used. |
|
20 | /// Added at the start of `.hg/dirstate` when the "v2" format is used. | |
21 | /// This a redundant sanity check more than an actual "magic number" since |
|
21 | /// This a redundant sanity check more than an actual "magic number" since | |
22 | /// `.hg/requires` already governs which format should be used. |
|
22 | /// `.hg/requires` already governs which format should be used. | |
23 | pub const V2_FORMAT_MARKER: &[u8; 12] = b"dirstate-v2\n"; |
|
23 | pub const V2_FORMAT_MARKER: &[u8; 12] = b"dirstate-v2\n"; | |
24 |
|
24 | |||
25 | /// Keep space for 256-bit hashes |
|
25 | /// Keep space for 256-bit hashes | |
26 | const STORED_NODE_ID_BYTES: usize = 32; |
|
26 | const STORED_NODE_ID_BYTES: usize = 32; | |
27 |
|
27 | |||
28 | /// β¦ even though only 160 bits are used for now, with SHA-1 |
|
28 | /// β¦ even though only 160 bits are used for now, with SHA-1 | |
29 | const USED_NODE_ID_BYTES: usize = 20; |
|
29 | const USED_NODE_ID_BYTES: usize = 20; | |
30 |
|
30 | |||
31 | pub(super) const IGNORE_PATTERNS_HASH_LEN: usize = 20; |
|
31 | pub(super) const IGNORE_PATTERNS_HASH_LEN: usize = 20; | |
32 | pub(super) type IgnorePatternsHash = [u8; IGNORE_PATTERNS_HASH_LEN]; |
|
32 | pub(super) type IgnorePatternsHash = [u8; IGNORE_PATTERNS_HASH_LEN]; | |
33 |
|
33 | |||
34 | /// Must match constants of the same names in `mercurial/dirstateutils/v2.py` |
|
34 | /// Must match constants of the same names in `mercurial/dirstateutils/v2.py` | |
35 | const TREE_METADATA_SIZE: usize = 44; |
|
35 | const TREE_METADATA_SIZE: usize = 44; | |
36 | const NODE_SIZE: usize = 44; |
|
36 | const NODE_SIZE: usize = 44; | |
37 |
|
37 | |||
38 | /// Make sure that size-affecting changes are made knowingly |
|
38 | /// Make sure that size-affecting changes are made knowingly | |
39 | #[allow(unused)] |
|
39 | #[allow(unused)] | |
40 | fn static_assert_size_of() { |
|
40 | fn static_assert_size_of() { | |
41 | let _ = std::mem::transmute::<TreeMetadata, [u8; TREE_METADATA_SIZE]>; |
|
41 | let _ = std::mem::transmute::<TreeMetadata, [u8; TREE_METADATA_SIZE]>; | |
42 | let _ = std::mem::transmute::<DocketHeader, [u8; TREE_METADATA_SIZE + 81]>; |
|
42 | let _ = std::mem::transmute::<DocketHeader, [u8; TREE_METADATA_SIZE + 81]>; | |
43 | let _ = std::mem::transmute::<Node, [u8; NODE_SIZE]>; |
|
43 | let _ = std::mem::transmute::<Node, [u8; NODE_SIZE]>; | |
44 | } |
|
44 | } | |
45 |
|
45 | |||
46 | // Must match `HEADER` in `mercurial/dirstateutils/docket.py` |
|
46 | // Must match `HEADER` in `mercurial/dirstateutils/docket.py` | |
47 | #[derive(BytesCast)] |
|
47 | #[derive(BytesCast)] | |
48 | #[repr(C)] |
|
48 | #[repr(C)] | |
49 | struct DocketHeader { |
|
49 | struct DocketHeader { | |
50 | marker: [u8; V2_FORMAT_MARKER.len()], |
|
50 | marker: [u8; V2_FORMAT_MARKER.len()], | |
51 | parent_1: [u8; STORED_NODE_ID_BYTES], |
|
51 | parent_1: [u8; STORED_NODE_ID_BYTES], | |
52 | parent_2: [u8; STORED_NODE_ID_BYTES], |
|
52 | parent_2: [u8; STORED_NODE_ID_BYTES], | |
53 |
|
53 | |||
54 | metadata: TreeMetadata, |
|
54 | metadata: TreeMetadata, | |
55 |
|
55 | |||
56 | /// Counted in bytes |
|
56 | /// Counted in bytes | |
57 | data_size: Size, |
|
57 | data_size: Size, | |
58 |
|
58 | |||
59 | uuid_size: u8, |
|
59 | uuid_size: u8, | |
60 | } |
|
60 | } | |
61 |
|
61 | |||
62 | pub struct Docket<'on_disk> { |
|
62 | pub struct Docket<'on_disk> { | |
63 | header: &'on_disk DocketHeader, |
|
63 | header: &'on_disk DocketHeader, | |
64 | uuid: &'on_disk [u8], |
|
64 | uuid: &'on_disk [u8], | |
65 | } |
|
65 | } | |
66 |
|
66 | |||
67 | /// Fields are documented in the *Tree metadata in the docket file* |
|
67 | /// Fields are documented in the *Tree metadata in the docket file* | |
68 | /// section of `mercurial/helptext/internals/dirstate-v2.txt` |
|
68 | /// section of `mercurial/helptext/internals/dirstate-v2.txt` | |
69 | #[derive(BytesCast)] |
|
69 | #[derive(BytesCast)] | |
70 | #[repr(C)] |
|
70 | #[repr(C)] | |
71 | struct TreeMetadata { |
|
71 | struct TreeMetadata { | |
72 | root_nodes: ChildNodes, |
|
72 | root_nodes: ChildNodes, | |
73 | nodes_with_entry_count: Size, |
|
73 | nodes_with_entry_count: Size, | |
74 | nodes_with_copy_source_count: Size, |
|
74 | nodes_with_copy_source_count: Size, | |
75 | unreachable_bytes: Size, |
|
75 | unreachable_bytes: Size, | |
76 | unused: [u8; 4], |
|
76 | unused: [u8; 4], | |
77 |
|
77 | |||
78 | /// See *Optional hash of ignore patterns* section of |
|
78 | /// See *Optional hash of ignore patterns* section of | |
79 | /// `mercurial/helptext/internals/dirstate-v2.txt` |
|
79 | /// `mercurial/helptext/internals/dirstate-v2.txt` | |
80 | ignore_patterns_hash: IgnorePatternsHash, |
|
80 | ignore_patterns_hash: IgnorePatternsHash, | |
81 | } |
|
81 | } | |
82 |
|
82 | |||
83 | /// Fields are documented in the *The data file format* |
|
83 | /// Fields are documented in the *The data file format* | |
84 | /// section of `mercurial/helptext/internals/dirstate-v2.txt` |
|
84 | /// section of `mercurial/helptext/internals/dirstate-v2.txt` | |
85 | #[derive(BytesCast)] |
|
85 | #[derive(BytesCast)] | |
86 | #[repr(C)] |
|
86 | #[repr(C)] | |
87 | pub(super) struct Node { |
|
87 | pub(super) struct Node { | |
88 | full_path: PathSlice, |
|
88 | full_path: PathSlice, | |
89 |
|
89 | |||
90 | /// In bytes from `self.full_path.start` |
|
90 | /// In bytes from `self.full_path.start` | |
91 | base_name_start: PathSize, |
|
91 | base_name_start: PathSize, | |
92 |
|
92 | |||
93 | copy_source: OptPathSlice, |
|
93 | copy_source: OptPathSlice, | |
94 | children: ChildNodes, |
|
94 | children: ChildNodes, | |
95 | pub(super) descendants_with_entry_count: Size, |
|
95 | pub(super) descendants_with_entry_count: Size, | |
96 | pub(super) tracked_descendants_count: Size, |
|
96 | pub(super) tracked_descendants_count: Size, | |
97 | flags: U16Be, |
|
97 | flags: U16Be, | |
98 | size: U32Be, |
|
98 | size: U32Be, | |
99 | mtime: PackedTruncatedTimestamp, |
|
99 | mtime: PackedTruncatedTimestamp, | |
100 | } |
|
100 | } | |
101 |
|
101 | |||
102 | bitflags! { |
|
102 | bitflags! { | |
103 | #[repr(C)] |
|
103 | #[repr(C)] | |
104 | struct Flags: u16 { |
|
104 | struct Flags: u16 { | |
105 | const WDIR_TRACKED = 1 << 0; |
|
105 | const WDIR_TRACKED = 1 << 0; | |
106 | const P1_TRACKED = 1 << 1; |
|
106 | const P1_TRACKED = 1 << 1; | |
107 | const P2_INFO = 1 << 2; |
|
107 | const P2_INFO = 1 << 2; | |
108 | const HAS_MODE_AND_SIZE = 1 << 3; |
|
108 | const HAS_MODE_AND_SIZE = 1 << 3; | |
109 | const HAS_MTIME = 1 << 4; |
|
109 | const HAS_FILE_MTIME = 1 << 4; | |
110 |
const |
|
110 | const HAS_DIRECTORY_MTIME = 1 << 5; | |
111 |
const MODE_ |
|
111 | const MODE_EXEC_PERM = 1 << 6; | |
|
112 | const MODE_IS_SYMLINK = 1 << 7; | |||
112 | } |
|
113 | } | |
113 | } |
|
114 | } | |
114 |
|
115 | |||
115 | /// Duration since the Unix epoch |
|
116 | /// Duration since the Unix epoch | |
116 | #[derive(BytesCast, Copy, Clone)] |
|
117 | #[derive(BytesCast, Copy, Clone)] | |
117 | #[repr(C)] |
|
118 | #[repr(C)] | |
118 | struct PackedTruncatedTimestamp { |
|
119 | struct PackedTruncatedTimestamp { | |
119 | truncated_seconds: U32Be, |
|
120 | truncated_seconds: U32Be, | |
120 | nanoseconds: U32Be, |
|
121 | nanoseconds: U32Be, | |
121 | } |
|
122 | } | |
122 |
|
123 | |||
123 | /// Counted in bytes from the start of the file |
|
124 | /// Counted in bytes from the start of the file | |
124 | /// |
|
125 | /// | |
125 | /// NOTE: not supporting `.hg/dirstate` files larger than 4 GiB. |
|
126 | /// NOTE: not supporting `.hg/dirstate` files larger than 4 GiB. | |
126 | type Offset = U32Be; |
|
127 | type Offset = U32Be; | |
127 |
|
128 | |||
128 | /// Counted in number of items |
|
129 | /// Counted in number of items | |
129 | /// |
|
130 | /// | |
130 | /// NOTE: we choose not to support counting more than 4 billion nodes anywhere. |
|
131 | /// NOTE: we choose not to support counting more than 4 billion nodes anywhere. | |
131 | type Size = U32Be; |
|
132 | type Size = U32Be; | |
132 |
|
133 | |||
133 | /// Counted in bytes |
|
134 | /// Counted in bytes | |
134 | /// |
|
135 | /// | |
135 | /// NOTE: we choose not to support file names/paths longer than 64 KiB. |
|
136 | /// NOTE: we choose not to support file names/paths longer than 64 KiB. | |
136 | type PathSize = U16Be; |
|
137 | type PathSize = U16Be; | |
137 |
|
138 | |||
138 | /// A contiguous sequence of `len` times `Node`, representing the child nodes |
|
139 | /// A contiguous sequence of `len` times `Node`, representing the child nodes | |
139 | /// of either some other node or of the repository root. |
|
140 | /// of either some other node or of the repository root. | |
140 | /// |
|
141 | /// | |
141 | /// Always sorted by ascending `full_path`, to allow binary search. |
|
142 | /// Always sorted by ascending `full_path`, to allow binary search. | |
142 | /// Since nodes with the same parent nodes also have the same parent path, |
|
143 | /// Since nodes with the same parent nodes also have the same parent path, | |
143 | /// only the `base_name`s need to be compared during binary search. |
|
144 | /// only the `base_name`s need to be compared during binary search. | |
144 | #[derive(BytesCast, Copy, Clone)] |
|
145 | #[derive(BytesCast, Copy, Clone)] | |
145 | #[repr(C)] |
|
146 | #[repr(C)] | |
146 | struct ChildNodes { |
|
147 | struct ChildNodes { | |
147 | start: Offset, |
|
148 | start: Offset, | |
148 | len: Size, |
|
149 | len: Size, | |
149 | } |
|
150 | } | |
150 |
|
151 | |||
151 | /// A `HgPath` of `len` bytes |
|
152 | /// A `HgPath` of `len` bytes | |
152 | #[derive(BytesCast, Copy, Clone)] |
|
153 | #[derive(BytesCast, Copy, Clone)] | |
153 | #[repr(C)] |
|
154 | #[repr(C)] | |
154 | struct PathSlice { |
|
155 | struct PathSlice { | |
155 | start: Offset, |
|
156 | start: Offset, | |
156 | len: PathSize, |
|
157 | len: PathSize, | |
157 | } |
|
158 | } | |
158 |
|
159 | |||
159 | /// Either nothing if `start == 0`, or a `HgPath` of `len` bytes |
|
160 | /// Either nothing if `start == 0`, or a `HgPath` of `len` bytes | |
160 | type OptPathSlice = PathSlice; |
|
161 | type OptPathSlice = PathSlice; | |
161 |
|
162 | |||
162 | /// Unexpected file format found in `.hg/dirstate` with the "v2" format. |
|
163 | /// Unexpected file format found in `.hg/dirstate` with the "v2" format. | |
163 | /// |
|
164 | /// | |
164 | /// This should only happen if Mercurial is buggy or a repository is corrupted. |
|
165 | /// This should only happen if Mercurial is buggy or a repository is corrupted. | |
165 | #[derive(Debug)] |
|
166 | #[derive(Debug)] | |
166 | pub struct DirstateV2ParseError; |
|
167 | pub struct DirstateV2ParseError; | |
167 |
|
168 | |||
168 | impl From<DirstateV2ParseError> for HgError { |
|
169 | impl From<DirstateV2ParseError> for HgError { | |
169 | fn from(_: DirstateV2ParseError) -> Self { |
|
170 | fn from(_: DirstateV2ParseError) -> Self { | |
170 | HgError::corrupted("dirstate-v2 parse error") |
|
171 | HgError::corrupted("dirstate-v2 parse error") | |
171 | } |
|
172 | } | |
172 | } |
|
173 | } | |
173 |
|
174 | |||
174 | impl From<DirstateV2ParseError> for crate::DirstateError { |
|
175 | impl From<DirstateV2ParseError> for crate::DirstateError { | |
175 | fn from(error: DirstateV2ParseError) -> Self { |
|
176 | fn from(error: DirstateV2ParseError) -> Self { | |
176 | HgError::from(error).into() |
|
177 | HgError::from(error).into() | |
177 | } |
|
178 | } | |
178 | } |
|
179 | } | |
179 |
|
180 | |||
180 | impl<'on_disk> Docket<'on_disk> { |
|
181 | impl<'on_disk> Docket<'on_disk> { | |
181 | pub fn parents(&self) -> DirstateParents { |
|
182 | pub fn parents(&self) -> DirstateParents { | |
182 | use crate::Node; |
|
183 | use crate::Node; | |
183 | let p1 = Node::try_from(&self.header.parent_1[..USED_NODE_ID_BYTES]) |
|
184 | let p1 = Node::try_from(&self.header.parent_1[..USED_NODE_ID_BYTES]) | |
184 | .unwrap() |
|
185 | .unwrap() | |
185 | .clone(); |
|
186 | .clone(); | |
186 | let p2 = Node::try_from(&self.header.parent_2[..USED_NODE_ID_BYTES]) |
|
187 | let p2 = Node::try_from(&self.header.parent_2[..USED_NODE_ID_BYTES]) | |
187 | .unwrap() |
|
188 | .unwrap() | |
188 | .clone(); |
|
189 | .clone(); | |
189 | DirstateParents { p1, p2 } |
|
190 | DirstateParents { p1, p2 } | |
190 | } |
|
191 | } | |
191 |
|
192 | |||
192 | pub fn tree_metadata(&self) -> &[u8] { |
|
193 | pub fn tree_metadata(&self) -> &[u8] { | |
193 | self.header.metadata.as_bytes() |
|
194 | self.header.metadata.as_bytes() | |
194 | } |
|
195 | } | |
195 |
|
196 | |||
196 | pub fn data_size(&self) -> usize { |
|
197 | pub fn data_size(&self) -> usize { | |
197 | // This `unwrap` could only panic on a 16-bit CPU |
|
198 | // This `unwrap` could only panic on a 16-bit CPU | |
198 | self.header.data_size.get().try_into().unwrap() |
|
199 | self.header.data_size.get().try_into().unwrap() | |
199 | } |
|
200 | } | |
200 |
|
201 | |||
201 | pub fn data_filename(&self) -> String { |
|
202 | pub fn data_filename(&self) -> String { | |
202 | String::from_utf8(format_bytes!(b"dirstate.{}", self.uuid)).unwrap() |
|
203 | String::from_utf8(format_bytes!(b"dirstate.{}", self.uuid)).unwrap() | |
203 | } |
|
204 | } | |
204 | } |
|
205 | } | |
205 |
|
206 | |||
206 | pub fn read_docket( |
|
207 | pub fn read_docket( | |
207 | on_disk: &[u8], |
|
208 | on_disk: &[u8], | |
208 | ) -> Result<Docket<'_>, DirstateV2ParseError> { |
|
209 | ) -> Result<Docket<'_>, DirstateV2ParseError> { | |
209 | let (header, uuid) = |
|
210 | let (header, uuid) = | |
210 | DocketHeader::from_bytes(on_disk).map_err(|_| DirstateV2ParseError)?; |
|
211 | DocketHeader::from_bytes(on_disk).map_err(|_| DirstateV2ParseError)?; | |
211 | let uuid_size = header.uuid_size as usize; |
|
212 | let uuid_size = header.uuid_size as usize; | |
212 | if header.marker == *V2_FORMAT_MARKER && uuid.len() == uuid_size { |
|
213 | if header.marker == *V2_FORMAT_MARKER && uuid.len() == uuid_size { | |
213 | Ok(Docket { header, uuid }) |
|
214 | Ok(Docket { header, uuid }) | |
214 | } else { |
|
215 | } else { | |
215 | Err(DirstateV2ParseError) |
|
216 | Err(DirstateV2ParseError) | |
216 | } |
|
217 | } | |
217 | } |
|
218 | } | |
218 |
|
219 | |||
219 | pub(super) fn read<'on_disk>( |
|
220 | pub(super) fn read<'on_disk>( | |
220 | on_disk: &'on_disk [u8], |
|
221 | on_disk: &'on_disk [u8], | |
221 | metadata: &[u8], |
|
222 | metadata: &[u8], | |
222 | ) -> Result<DirstateMap<'on_disk>, DirstateV2ParseError> { |
|
223 | ) -> Result<DirstateMap<'on_disk>, DirstateV2ParseError> { | |
223 | if on_disk.is_empty() { |
|
224 | if on_disk.is_empty() { | |
224 | return Ok(DirstateMap::empty(on_disk)); |
|
225 | return Ok(DirstateMap::empty(on_disk)); | |
225 | } |
|
226 | } | |
226 | let (meta, _) = TreeMetadata::from_bytes(metadata) |
|
227 | let (meta, _) = TreeMetadata::from_bytes(metadata) | |
227 | .map_err(|_| DirstateV2ParseError)?; |
|
228 | .map_err(|_| DirstateV2ParseError)?; | |
228 | let dirstate_map = DirstateMap { |
|
229 | let dirstate_map = DirstateMap { | |
229 | on_disk, |
|
230 | on_disk, | |
230 | root: dirstate_map::ChildNodes::OnDisk(read_nodes( |
|
231 | root: dirstate_map::ChildNodes::OnDisk(read_nodes( | |
231 | on_disk, |
|
232 | on_disk, | |
232 | meta.root_nodes, |
|
233 | meta.root_nodes, | |
233 | )?), |
|
234 | )?), | |
234 | nodes_with_entry_count: meta.nodes_with_entry_count.get(), |
|
235 | nodes_with_entry_count: meta.nodes_with_entry_count.get(), | |
235 | nodes_with_copy_source_count: meta.nodes_with_copy_source_count.get(), |
|
236 | nodes_with_copy_source_count: meta.nodes_with_copy_source_count.get(), | |
236 | ignore_patterns_hash: meta.ignore_patterns_hash, |
|
237 | ignore_patterns_hash: meta.ignore_patterns_hash, | |
237 | unreachable_bytes: meta.unreachable_bytes.get(), |
|
238 | unreachable_bytes: meta.unreachable_bytes.get(), | |
238 | }; |
|
239 | }; | |
239 | Ok(dirstate_map) |
|
240 | Ok(dirstate_map) | |
240 | } |
|
241 | } | |
241 |
|
242 | |||
242 | impl Node { |
|
243 | impl Node { | |
243 | pub(super) fn full_path<'on_disk>( |
|
244 | pub(super) fn full_path<'on_disk>( | |
244 | &self, |
|
245 | &self, | |
245 | on_disk: &'on_disk [u8], |
|
246 | on_disk: &'on_disk [u8], | |
246 | ) -> Result<&'on_disk HgPath, DirstateV2ParseError> { |
|
247 | ) -> Result<&'on_disk HgPath, DirstateV2ParseError> { | |
247 | read_hg_path(on_disk, self.full_path) |
|
248 | read_hg_path(on_disk, self.full_path) | |
248 | } |
|
249 | } | |
249 |
|
250 | |||
250 | pub(super) fn base_name_start<'on_disk>( |
|
251 | pub(super) fn base_name_start<'on_disk>( | |
251 | &self, |
|
252 | &self, | |
252 | ) -> Result<usize, DirstateV2ParseError> { |
|
253 | ) -> Result<usize, DirstateV2ParseError> { | |
253 | let start = self.base_name_start.get(); |
|
254 | let start = self.base_name_start.get(); | |
254 | if start < self.full_path.len.get() { |
|
255 | if start < self.full_path.len.get() { | |
255 | let start = usize::try_from(start) |
|
256 | let start = usize::try_from(start) | |
256 | // u32 -> usize, could only panic on a 16-bit CPU |
|
257 | // u32 -> usize, could only panic on a 16-bit CPU | |
257 | .expect("dirstate-v2 base_name_start out of bounds"); |
|
258 | .expect("dirstate-v2 base_name_start out of bounds"); | |
258 | Ok(start) |
|
259 | Ok(start) | |
259 | } else { |
|
260 | } else { | |
260 | Err(DirstateV2ParseError) |
|
261 | Err(DirstateV2ParseError) | |
261 | } |
|
262 | } | |
262 | } |
|
263 | } | |
263 |
|
264 | |||
264 | pub(super) fn base_name<'on_disk>( |
|
265 | pub(super) fn base_name<'on_disk>( | |
265 | &self, |
|
266 | &self, | |
266 | on_disk: &'on_disk [u8], |
|
267 | on_disk: &'on_disk [u8], | |
267 | ) -> Result<&'on_disk HgPath, DirstateV2ParseError> { |
|
268 | ) -> Result<&'on_disk HgPath, DirstateV2ParseError> { | |
268 | let full_path = self.full_path(on_disk)?; |
|
269 | let full_path = self.full_path(on_disk)?; | |
269 | let base_name_start = self.base_name_start()?; |
|
270 | let base_name_start = self.base_name_start()?; | |
270 | Ok(HgPath::new(&full_path.as_bytes()[base_name_start..])) |
|
271 | Ok(HgPath::new(&full_path.as_bytes()[base_name_start..])) | |
271 | } |
|
272 | } | |
272 |
|
273 | |||
273 | pub(super) fn path<'on_disk>( |
|
274 | pub(super) fn path<'on_disk>( | |
274 | &self, |
|
275 | &self, | |
275 | on_disk: &'on_disk [u8], |
|
276 | on_disk: &'on_disk [u8], | |
276 | ) -> Result<dirstate_map::NodeKey<'on_disk>, DirstateV2ParseError> { |
|
277 | ) -> Result<dirstate_map::NodeKey<'on_disk>, DirstateV2ParseError> { | |
277 | Ok(WithBasename::from_raw_parts( |
|
278 | Ok(WithBasename::from_raw_parts( | |
278 | Cow::Borrowed(self.full_path(on_disk)?), |
|
279 | Cow::Borrowed(self.full_path(on_disk)?), | |
279 | self.base_name_start()?, |
|
280 | self.base_name_start()?, | |
280 | )) |
|
281 | )) | |
281 | } |
|
282 | } | |
282 |
|
283 | |||
283 | pub(super) fn has_copy_source<'on_disk>(&self) -> bool { |
|
284 | pub(super) fn has_copy_source<'on_disk>(&self) -> bool { | |
284 | self.copy_source.start.get() != 0 |
|
285 | self.copy_source.start.get() != 0 | |
285 | } |
|
286 | } | |
286 |
|
287 | |||
287 | pub(super) fn copy_source<'on_disk>( |
|
288 | pub(super) fn copy_source<'on_disk>( | |
288 | &self, |
|
289 | &self, | |
289 | on_disk: &'on_disk [u8], |
|
290 | on_disk: &'on_disk [u8], | |
290 | ) -> Result<Option<&'on_disk HgPath>, DirstateV2ParseError> { |
|
291 | ) -> Result<Option<&'on_disk HgPath>, DirstateV2ParseError> { | |
291 | Ok(if self.has_copy_source() { |
|
292 | Ok(if self.has_copy_source() { | |
292 | Some(read_hg_path(on_disk, self.copy_source)?) |
|
293 | Some(read_hg_path(on_disk, self.copy_source)?) | |
293 | } else { |
|
294 | } else { | |
294 | None |
|
295 | None | |
295 | }) |
|
296 | }) | |
296 | } |
|
297 | } | |
297 |
|
298 | |||
298 | fn flags(&self) -> Flags { |
|
299 | fn flags(&self) -> Flags { | |
299 | Flags::from_bits_truncate(self.flags.get()) |
|
300 | Flags::from_bits_truncate(self.flags.get()) | |
300 | } |
|
301 | } | |
301 |
|
302 | |||
302 | fn has_entry(&self) -> bool { |
|
303 | fn has_entry(&self) -> bool { | |
303 | self.flags().intersects( |
|
304 | self.flags().intersects( | |
304 | Flags::WDIR_TRACKED | Flags::P1_TRACKED | Flags::P2_INFO, |
|
305 | Flags::WDIR_TRACKED | Flags::P1_TRACKED | Flags::P2_INFO, | |
305 | ) |
|
306 | ) | |
306 | } |
|
307 | } | |
307 |
|
308 | |||
308 | pub(super) fn node_data( |
|
309 | pub(super) fn node_data( | |
309 | &self, |
|
310 | &self, | |
310 | ) -> Result<dirstate_map::NodeData, DirstateV2ParseError> { |
|
311 | ) -> Result<dirstate_map::NodeData, DirstateV2ParseError> { | |
311 | if self.has_entry() { |
|
312 | if self.has_entry() { | |
312 | Ok(dirstate_map::NodeData::Entry(self.assume_entry())) |
|
313 | Ok(dirstate_map::NodeData::Entry(self.assume_entry())) | |
313 | } else if let Some(mtime) = self.cached_directory_mtime()? { |
|
314 | } else if let Some(mtime) = self.cached_directory_mtime()? { | |
314 | Ok(dirstate_map::NodeData::CachedDirectory { mtime }) |
|
315 | Ok(dirstate_map::NodeData::CachedDirectory { mtime }) | |
315 | } else { |
|
316 | } else { | |
316 | Ok(dirstate_map::NodeData::None) |
|
317 | Ok(dirstate_map::NodeData::None) | |
317 | } |
|
318 | } | |
318 | } |
|
319 | } | |
319 |
|
320 | |||
320 | pub(super) fn cached_directory_mtime( |
|
321 | pub(super) fn cached_directory_mtime( | |
321 | &self, |
|
322 | &self, | |
322 | ) -> Result<Option<TruncatedTimestamp>, DirstateV2ParseError> { |
|
323 | ) -> Result<Option<TruncatedTimestamp>, DirstateV2ParseError> { | |
323 | Ok( |
|
324 | if self.flags().contains(Flags::HAS_DIRECTORY_MTIME) { | |
324 |
if self.flags().contains(Flags::HAS_MTIME |
|
325 | if self.flags().contains(Flags::HAS_FILE_MTIME) { | |
325 | Some(self.mtime.try_into()?) |
|
326 | Err(DirstateV2ParseError) | |
326 | } else { |
|
327 | } else { | |
327 | None |
|
328 | Ok(Some(self.mtime.try_into()?)) | |
328 |
} |
|
329 | } | |
329 |
|
|
330 | } else { | |
|
331 | Ok(None) | |||
|
332 | } | |||
330 | } |
|
333 | } | |
331 |
|
334 | |||
332 | fn synthesize_unix_mode(&self) -> u32 { |
|
335 | fn synthesize_unix_mode(&self) -> u32 { | |
333 | let file_type = if self.flags().contains(Flags::MODE_IS_SYMLINK) { |
|
336 | let file_type = if self.flags().contains(Flags::MODE_IS_SYMLINK) { | |
334 | libc::S_IFLNK |
|
337 | libc::S_IFLNK | |
335 | } else { |
|
338 | } else { | |
336 | libc::S_IFREG |
|
339 | libc::S_IFREG | |
337 | }; |
|
340 | }; | |
338 | let permisions = if self.flags().contains(Flags::MODE_EXEC_PERM) { |
|
341 | let permisions = if self.flags().contains(Flags::MODE_EXEC_PERM) { | |
339 | 0o755 |
|
342 | 0o755 | |
340 | } else { |
|
343 | } else { | |
341 | 0o644 |
|
344 | 0o644 | |
342 | }; |
|
345 | }; | |
343 | file_type | permisions |
|
346 | file_type | permisions | |
344 | } |
|
347 | } | |
345 |
|
348 | |||
346 | fn assume_entry(&self) -> DirstateEntry { |
|
349 | fn assume_entry(&self) -> DirstateEntry { | |
347 | // TODO: convert through raw bits instead? |
|
350 | // TODO: convert through raw bits instead? | |
348 | let wdir_tracked = self.flags().contains(Flags::WDIR_TRACKED); |
|
351 | let wdir_tracked = self.flags().contains(Flags::WDIR_TRACKED); | |
349 | let p1_tracked = self.flags().contains(Flags::P1_TRACKED); |
|
352 | let p1_tracked = self.flags().contains(Flags::P1_TRACKED); | |
350 | let p2_info = self.flags().contains(Flags::P2_INFO); |
|
353 | let p2_info = self.flags().contains(Flags::P2_INFO); | |
351 | let mode_size = if self.flags().contains(Flags::HAS_MODE_AND_SIZE) { |
|
354 | let mode_size = if self.flags().contains(Flags::HAS_MODE_AND_SIZE) { | |
352 | Some((self.synthesize_unix_mode(), self.size.into())) |
|
355 | Some((self.synthesize_unix_mode(), self.size.into())) | |
353 | } else { |
|
356 | } else { | |
354 | None |
|
357 | None | |
355 | }; |
|
358 | }; | |
356 | let mtime = if self.flags().contains(Flags::HAS_MTIME) { |
|
359 | let mtime = if self.flags().contains(Flags::HAS_FILE_MTIME) { | |
357 | Some(self.mtime.truncated_seconds.into()) |
|
360 | Some(self.mtime.truncated_seconds.into()) | |
358 | } else { |
|
361 | } else { | |
359 | None |
|
362 | None | |
360 | }; |
|
363 | }; | |
361 | DirstateEntry::from_v2_data( |
|
364 | DirstateEntry::from_v2_data( | |
362 | wdir_tracked, |
|
365 | wdir_tracked, | |
363 | p1_tracked, |
|
366 | p1_tracked, | |
364 | p2_info, |
|
367 | p2_info, | |
365 | mode_size, |
|
368 | mode_size, | |
366 | mtime, |
|
369 | mtime, | |
367 | ) |
|
370 | ) | |
368 | } |
|
371 | } | |
369 |
|
372 | |||
370 | pub(super) fn entry( |
|
373 | pub(super) fn entry( | |
371 | &self, |
|
374 | &self, | |
372 | ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> { |
|
375 | ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> { | |
373 | if self.has_entry() { |
|
376 | if self.has_entry() { | |
374 | Ok(Some(self.assume_entry())) |
|
377 | Ok(Some(self.assume_entry())) | |
375 | } else { |
|
378 | } else { | |
376 | Ok(None) |
|
379 | Ok(None) | |
377 | } |
|
380 | } | |
378 | } |
|
381 | } | |
379 |
|
382 | |||
380 | pub(super) fn children<'on_disk>( |
|
383 | pub(super) fn children<'on_disk>( | |
381 | &self, |
|
384 | &self, | |
382 | on_disk: &'on_disk [u8], |
|
385 | on_disk: &'on_disk [u8], | |
383 | ) -> Result<&'on_disk [Node], DirstateV2ParseError> { |
|
386 | ) -> Result<&'on_disk [Node], DirstateV2ParseError> { | |
384 | read_nodes(on_disk, self.children) |
|
387 | read_nodes(on_disk, self.children) | |
385 | } |
|
388 | } | |
386 |
|
389 | |||
387 | pub(super) fn to_in_memory_node<'on_disk>( |
|
390 | pub(super) fn to_in_memory_node<'on_disk>( | |
388 | &self, |
|
391 | &self, | |
389 | on_disk: &'on_disk [u8], |
|
392 | on_disk: &'on_disk [u8], | |
390 | ) -> Result<dirstate_map::Node<'on_disk>, DirstateV2ParseError> { |
|
393 | ) -> Result<dirstate_map::Node<'on_disk>, DirstateV2ParseError> { | |
391 | Ok(dirstate_map::Node { |
|
394 | Ok(dirstate_map::Node { | |
392 | children: dirstate_map::ChildNodes::OnDisk( |
|
395 | children: dirstate_map::ChildNodes::OnDisk( | |
393 | self.children(on_disk)?, |
|
396 | self.children(on_disk)?, | |
394 | ), |
|
397 | ), | |
395 | copy_source: self.copy_source(on_disk)?.map(Cow::Borrowed), |
|
398 | copy_source: self.copy_source(on_disk)?.map(Cow::Borrowed), | |
396 | data: self.node_data()?, |
|
399 | data: self.node_data()?, | |
397 | descendants_with_entry_count: self |
|
400 | descendants_with_entry_count: self | |
398 | .descendants_with_entry_count |
|
401 | .descendants_with_entry_count | |
399 | .get(), |
|
402 | .get(), | |
400 | tracked_descendants_count: self.tracked_descendants_count.get(), |
|
403 | tracked_descendants_count: self.tracked_descendants_count.get(), | |
401 | }) |
|
404 | }) | |
402 | } |
|
405 | } | |
403 |
|
406 | |||
404 | fn from_dirstate_entry( |
|
407 | fn from_dirstate_entry( | |
405 | entry: &DirstateEntry, |
|
408 | entry: &DirstateEntry, | |
406 | ) -> (Flags, U32Be, PackedTruncatedTimestamp) { |
|
409 | ) -> (Flags, U32Be, PackedTruncatedTimestamp) { | |
407 | let (wdir_tracked, p1_tracked, p2_info, mode_size_opt, mtime_opt) = |
|
410 | let (wdir_tracked, p1_tracked, p2_info, mode_size_opt, mtime_opt) = | |
408 | entry.v2_data(); |
|
411 | entry.v2_data(); | |
409 | // TODO: convert throug raw flag bits instead? |
|
412 | // TODO: convert throug raw flag bits instead? | |
410 | let mut flags = Flags::empty(); |
|
413 | let mut flags = Flags::empty(); | |
411 | flags.set(Flags::WDIR_TRACKED, wdir_tracked); |
|
414 | flags.set(Flags::WDIR_TRACKED, wdir_tracked); | |
412 | flags.set(Flags::P1_TRACKED, p1_tracked); |
|
415 | flags.set(Flags::P1_TRACKED, p1_tracked); | |
413 | flags.set(Flags::P2_INFO, p2_info); |
|
416 | flags.set(Flags::P2_INFO, p2_info); | |
414 | let size = if let Some((m, s)) = mode_size_opt { |
|
417 | let size = if let Some((m, s)) = mode_size_opt { | |
415 | let exec_perm = m & libc::S_IXUSR != 0; |
|
418 | let exec_perm = m & libc::S_IXUSR != 0; | |
416 | let is_symlink = m & libc::S_IFMT == libc::S_IFLNK; |
|
419 | let is_symlink = m & libc::S_IFMT == libc::S_IFLNK; | |
417 | flags.set(Flags::MODE_EXEC_PERM, exec_perm); |
|
420 | flags.set(Flags::MODE_EXEC_PERM, exec_perm); | |
418 | flags.set(Flags::MODE_IS_SYMLINK, is_symlink); |
|
421 | flags.set(Flags::MODE_IS_SYMLINK, is_symlink); | |
419 | flags.insert(Flags::HAS_MODE_AND_SIZE); |
|
422 | flags.insert(Flags::HAS_MODE_AND_SIZE); | |
420 | s.into() |
|
423 | s.into() | |
421 | } else { |
|
424 | } else { | |
422 | 0.into() |
|
425 | 0.into() | |
423 | }; |
|
426 | }; | |
424 | let mtime = if let Some(m) = mtime_opt { |
|
427 | let mtime = if let Some(m) = mtime_opt { | |
425 | flags.insert(Flags::HAS_MTIME); |
|
428 | flags.insert(Flags::HAS_FILE_MTIME); | |
426 | PackedTruncatedTimestamp { |
|
429 | PackedTruncatedTimestamp { | |
427 | truncated_seconds: m.into(), |
|
430 | truncated_seconds: m.into(), | |
428 | nanoseconds: 0.into(), |
|
431 | nanoseconds: 0.into(), | |
429 | } |
|
432 | } | |
430 | } else { |
|
433 | } else { | |
431 | PackedTruncatedTimestamp::null() |
|
434 | PackedTruncatedTimestamp::null() | |
432 | }; |
|
435 | }; | |
433 | (flags, size, mtime) |
|
436 | (flags, size, mtime) | |
434 | } |
|
437 | } | |
435 | } |
|
438 | } | |
436 |
|
439 | |||
437 | fn read_hg_path( |
|
440 | fn read_hg_path( | |
438 | on_disk: &[u8], |
|
441 | on_disk: &[u8], | |
439 | slice: PathSlice, |
|
442 | slice: PathSlice, | |
440 | ) -> Result<&HgPath, DirstateV2ParseError> { |
|
443 | ) -> Result<&HgPath, DirstateV2ParseError> { | |
441 | read_slice(on_disk, slice.start, slice.len.get()).map(HgPath::new) |
|
444 | read_slice(on_disk, slice.start, slice.len.get()).map(HgPath::new) | |
442 | } |
|
445 | } | |
443 |
|
446 | |||
444 | fn read_nodes( |
|
447 | fn read_nodes( | |
445 | on_disk: &[u8], |
|
448 | on_disk: &[u8], | |
446 | slice: ChildNodes, |
|
449 | slice: ChildNodes, | |
447 | ) -> Result<&[Node], DirstateV2ParseError> { |
|
450 | ) -> Result<&[Node], DirstateV2ParseError> { | |
448 | read_slice(on_disk, slice.start, slice.len.get()) |
|
451 | read_slice(on_disk, slice.start, slice.len.get()) | |
449 | } |
|
452 | } | |
450 |
|
453 | |||
451 | fn read_slice<T, Len>( |
|
454 | fn read_slice<T, Len>( | |
452 | on_disk: &[u8], |
|
455 | on_disk: &[u8], | |
453 | start: Offset, |
|
456 | start: Offset, | |
454 | len: Len, |
|
457 | len: Len, | |
455 | ) -> Result<&[T], DirstateV2ParseError> |
|
458 | ) -> Result<&[T], DirstateV2ParseError> | |
456 | where |
|
459 | where | |
457 | T: BytesCast, |
|
460 | T: BytesCast, | |
458 | Len: TryInto<usize>, |
|
461 | Len: TryInto<usize>, | |
459 | { |
|
462 | { | |
460 | // Either `usize::MAX` would result in "out of bounds" error since a single |
|
463 | // Either `usize::MAX` would result in "out of bounds" error since a single | |
461 | // `&[u8]` cannot occupy the entire addess space. |
|
464 | // `&[u8]` cannot occupy the entire addess space. | |
462 | let start = start.get().try_into().unwrap_or(std::usize::MAX); |
|
465 | let start = start.get().try_into().unwrap_or(std::usize::MAX); | |
463 | let len = len.try_into().unwrap_or(std::usize::MAX); |
|
466 | let len = len.try_into().unwrap_or(std::usize::MAX); | |
464 | on_disk |
|
467 | on_disk | |
465 | .get(start..) |
|
468 | .get(start..) | |
466 | .and_then(|bytes| T::slice_from_bytes(bytes, len).ok()) |
|
469 | .and_then(|bytes| T::slice_from_bytes(bytes, len).ok()) | |
467 | .map(|(slice, _rest)| slice) |
|
470 | .map(|(slice, _rest)| slice) | |
468 | .ok_or_else(|| DirstateV2ParseError) |
|
471 | .ok_or_else(|| DirstateV2ParseError) | |
469 | } |
|
472 | } | |
470 |
|
473 | |||
471 | pub(crate) fn for_each_tracked_path<'on_disk>( |
|
474 | pub(crate) fn for_each_tracked_path<'on_disk>( | |
472 | on_disk: &'on_disk [u8], |
|
475 | on_disk: &'on_disk [u8], | |
473 | metadata: &[u8], |
|
476 | metadata: &[u8], | |
474 | mut f: impl FnMut(&'on_disk HgPath), |
|
477 | mut f: impl FnMut(&'on_disk HgPath), | |
475 | ) -> Result<(), DirstateV2ParseError> { |
|
478 | ) -> Result<(), DirstateV2ParseError> { | |
476 | let (meta, _) = TreeMetadata::from_bytes(metadata) |
|
479 | let (meta, _) = TreeMetadata::from_bytes(metadata) | |
477 | .map_err(|_| DirstateV2ParseError)?; |
|
480 | .map_err(|_| DirstateV2ParseError)?; | |
478 | fn recur<'on_disk>( |
|
481 | fn recur<'on_disk>( | |
479 | on_disk: &'on_disk [u8], |
|
482 | on_disk: &'on_disk [u8], | |
480 | nodes: ChildNodes, |
|
483 | nodes: ChildNodes, | |
481 | f: &mut impl FnMut(&'on_disk HgPath), |
|
484 | f: &mut impl FnMut(&'on_disk HgPath), | |
482 | ) -> Result<(), DirstateV2ParseError> { |
|
485 | ) -> Result<(), DirstateV2ParseError> { | |
483 | for node in read_nodes(on_disk, nodes)? { |
|
486 | for node in read_nodes(on_disk, nodes)? { | |
484 | if let Some(entry) = node.entry()? { |
|
487 | if let Some(entry) = node.entry()? { | |
485 | if entry.state().is_tracked() { |
|
488 | if entry.state().is_tracked() { | |
486 | f(node.full_path(on_disk)?) |
|
489 | f(node.full_path(on_disk)?) | |
487 | } |
|
490 | } | |
488 | } |
|
491 | } | |
489 | recur(on_disk, node.children, f)? |
|
492 | recur(on_disk, node.children, f)? | |
490 | } |
|
493 | } | |
491 | Ok(()) |
|
494 | Ok(()) | |
492 | } |
|
495 | } | |
493 | recur(on_disk, meta.root_nodes, &mut f) |
|
496 | recur(on_disk, meta.root_nodes, &mut f) | |
494 | } |
|
497 | } | |
495 |
|
498 | |||
496 | /// Returns new data and metadata, together with whether that data should be |
|
499 | /// Returns new data and metadata, together with whether that data should be | |
497 | /// appended to the existing data file whose content is at |
|
500 | /// appended to the existing data file whose content is at | |
498 | /// `dirstate_map.on_disk` (true), instead of written to a new data file |
|
501 | /// `dirstate_map.on_disk` (true), instead of written to a new data file | |
499 | /// (false). |
|
502 | /// (false). | |
500 | pub(super) fn write( |
|
503 | pub(super) fn write( | |
501 | dirstate_map: &mut DirstateMap, |
|
504 | dirstate_map: &mut DirstateMap, | |
502 | can_append: bool, |
|
505 | can_append: bool, | |
503 | ) -> Result<(Vec<u8>, Vec<u8>, bool), DirstateError> { |
|
506 | ) -> Result<(Vec<u8>, Vec<u8>, bool), DirstateError> { | |
504 | let append = can_append && dirstate_map.write_should_append(); |
|
507 | let append = can_append && dirstate_map.write_should_append(); | |
505 |
|
508 | |||
506 | // This ignores the space for paths, and for nodes without an entry. |
|
509 | // This ignores the space for paths, and for nodes without an entry. | |
507 | // TODO: better estimate? Skip the `Vec` and write to a file directly? |
|
510 | // TODO: better estimate? Skip the `Vec` and write to a file directly? | |
508 | let size_guess = std::mem::size_of::<Node>() |
|
511 | let size_guess = std::mem::size_of::<Node>() | |
509 | * dirstate_map.nodes_with_entry_count as usize; |
|
512 | * dirstate_map.nodes_with_entry_count as usize; | |
510 |
|
513 | |||
511 | let mut writer = Writer { |
|
514 | let mut writer = Writer { | |
512 | dirstate_map, |
|
515 | dirstate_map, | |
513 | append, |
|
516 | append, | |
514 | out: Vec::with_capacity(size_guess), |
|
517 | out: Vec::with_capacity(size_guess), | |
515 | }; |
|
518 | }; | |
516 |
|
519 | |||
517 | let root_nodes = writer.write_nodes(dirstate_map.root.as_ref())?; |
|
520 | let root_nodes = writer.write_nodes(dirstate_map.root.as_ref())?; | |
518 |
|
521 | |||
519 | let meta = TreeMetadata { |
|
522 | let meta = TreeMetadata { | |
520 | root_nodes, |
|
523 | root_nodes, | |
521 | nodes_with_entry_count: dirstate_map.nodes_with_entry_count.into(), |
|
524 | nodes_with_entry_count: dirstate_map.nodes_with_entry_count.into(), | |
522 | nodes_with_copy_source_count: dirstate_map |
|
525 | nodes_with_copy_source_count: dirstate_map | |
523 | .nodes_with_copy_source_count |
|
526 | .nodes_with_copy_source_count | |
524 | .into(), |
|
527 | .into(), | |
525 | unreachable_bytes: dirstate_map.unreachable_bytes.into(), |
|
528 | unreachable_bytes: dirstate_map.unreachable_bytes.into(), | |
526 | unused: [0; 4], |
|
529 | unused: [0; 4], | |
527 | ignore_patterns_hash: dirstate_map.ignore_patterns_hash, |
|
530 | ignore_patterns_hash: dirstate_map.ignore_patterns_hash, | |
528 | }; |
|
531 | }; | |
529 | Ok((writer.out, meta.as_bytes().to_vec(), append)) |
|
532 | Ok((writer.out, meta.as_bytes().to_vec(), append)) | |
530 | } |
|
533 | } | |
531 |
|
534 | |||
532 | struct Writer<'dmap, 'on_disk> { |
|
535 | struct Writer<'dmap, 'on_disk> { | |
533 | dirstate_map: &'dmap DirstateMap<'on_disk>, |
|
536 | dirstate_map: &'dmap DirstateMap<'on_disk>, | |
534 | append: bool, |
|
537 | append: bool, | |
535 | out: Vec<u8>, |
|
538 | out: Vec<u8>, | |
536 | } |
|
539 | } | |
537 |
|
540 | |||
538 | impl Writer<'_, '_> { |
|
541 | impl Writer<'_, '_> { | |
539 | fn write_nodes( |
|
542 | fn write_nodes( | |
540 | &mut self, |
|
543 | &mut self, | |
541 | nodes: dirstate_map::ChildNodesRef, |
|
544 | nodes: dirstate_map::ChildNodesRef, | |
542 | ) -> Result<ChildNodes, DirstateError> { |
|
545 | ) -> Result<ChildNodes, DirstateError> { | |
543 | // Reuse already-written nodes if possible |
|
546 | // Reuse already-written nodes if possible | |
544 | if self.append { |
|
547 | if self.append { | |
545 | if let dirstate_map::ChildNodesRef::OnDisk(nodes_slice) = nodes { |
|
548 | if let dirstate_map::ChildNodesRef::OnDisk(nodes_slice) = nodes { | |
546 | let start = self.on_disk_offset_of(nodes_slice).expect( |
|
549 | let start = self.on_disk_offset_of(nodes_slice).expect( | |
547 | "dirstate-v2 OnDisk nodes not found within on_disk", |
|
550 | "dirstate-v2 OnDisk nodes not found within on_disk", | |
548 | ); |
|
551 | ); | |
549 | let len = child_nodes_len_from_usize(nodes_slice.len()); |
|
552 | let len = child_nodes_len_from_usize(nodes_slice.len()); | |
550 | return Ok(ChildNodes { start, len }); |
|
553 | return Ok(ChildNodes { start, len }); | |
551 | } |
|
554 | } | |
552 | } |
|
555 | } | |
553 |
|
556 | |||
554 | // `dirstate_map::ChildNodes::InMemory` contains a `HashMap` which has |
|
557 | // `dirstate_map::ChildNodes::InMemory` contains a `HashMap` which has | |
555 | // undefined iteration order. Sort to enable binary search in the |
|
558 | // undefined iteration order. Sort to enable binary search in the | |
556 | // written file. |
|
559 | // written file. | |
557 | let nodes = nodes.sorted(); |
|
560 | let nodes = nodes.sorted(); | |
558 | let nodes_len = nodes.len(); |
|
561 | let nodes_len = nodes.len(); | |
559 |
|
562 | |||
560 | // First accumulate serialized nodes in a `Vec` |
|
563 | // First accumulate serialized nodes in a `Vec` | |
561 | let mut on_disk_nodes = Vec::with_capacity(nodes_len); |
|
564 | let mut on_disk_nodes = Vec::with_capacity(nodes_len); | |
562 | for node in nodes { |
|
565 | for node in nodes { | |
563 | let children = |
|
566 | let children = | |
564 | self.write_nodes(node.children(self.dirstate_map.on_disk)?)?; |
|
567 | self.write_nodes(node.children(self.dirstate_map.on_disk)?)?; | |
565 | let full_path = node.full_path(self.dirstate_map.on_disk)?; |
|
568 | let full_path = node.full_path(self.dirstate_map.on_disk)?; | |
566 | let full_path = self.write_path(full_path.as_bytes()); |
|
569 | let full_path = self.write_path(full_path.as_bytes()); | |
567 | let copy_source = if let Some(source) = |
|
570 | let copy_source = if let Some(source) = | |
568 | node.copy_source(self.dirstate_map.on_disk)? |
|
571 | node.copy_source(self.dirstate_map.on_disk)? | |
569 | { |
|
572 | { | |
570 | self.write_path(source.as_bytes()) |
|
573 | self.write_path(source.as_bytes()) | |
571 | } else { |
|
574 | } else { | |
572 | PathSlice { |
|
575 | PathSlice { | |
573 | start: 0.into(), |
|
576 | start: 0.into(), | |
574 | len: 0.into(), |
|
577 | len: 0.into(), | |
575 | } |
|
578 | } | |
576 | }; |
|
579 | }; | |
577 | on_disk_nodes.push(match node { |
|
580 | on_disk_nodes.push(match node { | |
578 | NodeRef::InMemory(path, node) => { |
|
581 | NodeRef::InMemory(path, node) => { | |
579 | let (flags, size, mtime) = match &node.data { |
|
582 | let (flags, size, mtime) = match &node.data { | |
580 | dirstate_map::NodeData::Entry(entry) => { |
|
583 | dirstate_map::NodeData::Entry(entry) => { | |
581 | Node::from_dirstate_entry(entry) |
|
584 | Node::from_dirstate_entry(entry) | |
582 | } |
|
585 | } | |
583 |
dirstate_map::NodeData::CachedDirectory { mtime } => |
|
586 | dirstate_map::NodeData::CachedDirectory { mtime } => ( | |
584 |
|
|
587 | Flags::HAS_DIRECTORY_MTIME, | |
585 |
|
|
588 | 0.into(), | |
|
589 | (*mtime).into(), | |||
|
590 | ), | |||
586 | dirstate_map::NodeData::None => ( |
|
591 | dirstate_map::NodeData::None => ( | |
587 | Flags::empty(), |
|
592 | Flags::empty(), | |
588 | 0.into(), |
|
593 | 0.into(), | |
589 | PackedTruncatedTimestamp::null(), |
|
594 | PackedTruncatedTimestamp::null(), | |
590 | ), |
|
595 | ), | |
591 | }; |
|
596 | }; | |
592 | Node { |
|
597 | Node { | |
593 | children, |
|
598 | children, | |
594 | copy_source, |
|
599 | copy_source, | |
595 | full_path, |
|
600 | full_path, | |
596 | base_name_start: u16::try_from(path.base_name_start()) |
|
601 | base_name_start: u16::try_from(path.base_name_start()) | |
597 | // Could only panic for paths over 64 KiB |
|
602 | // Could only panic for paths over 64 KiB | |
598 | .expect("dirstate-v2 path length overflow") |
|
603 | .expect("dirstate-v2 path length overflow") | |
599 | .into(), |
|
604 | .into(), | |
600 | descendants_with_entry_count: node |
|
605 | descendants_with_entry_count: node | |
601 | .descendants_with_entry_count |
|
606 | .descendants_with_entry_count | |
602 | .into(), |
|
607 | .into(), | |
603 | tracked_descendants_count: node |
|
608 | tracked_descendants_count: node | |
604 | .tracked_descendants_count |
|
609 | .tracked_descendants_count | |
605 | .into(), |
|
610 | .into(), | |
606 | flags: flags.bits().into(), |
|
611 | flags: flags.bits().into(), | |
607 | size, |
|
612 | size, | |
608 | mtime, |
|
613 | mtime, | |
609 | } |
|
614 | } | |
610 | } |
|
615 | } | |
611 | NodeRef::OnDisk(node) => Node { |
|
616 | NodeRef::OnDisk(node) => Node { | |
612 | children, |
|
617 | children, | |
613 | copy_source, |
|
618 | copy_source, | |
614 | full_path, |
|
619 | full_path, | |
615 | ..*node |
|
620 | ..*node | |
616 | }, |
|
621 | }, | |
617 | }) |
|
622 | }) | |
618 | } |
|
623 | } | |
619 | // β¦ so we can write them contiguously, after writing everything else |
|
624 | // β¦ so we can write them contiguously, after writing everything else | |
620 | // they refer to. |
|
625 | // they refer to. | |
621 | let start = self.current_offset(); |
|
626 | let start = self.current_offset(); | |
622 | let len = child_nodes_len_from_usize(nodes_len); |
|
627 | let len = child_nodes_len_from_usize(nodes_len); | |
623 | self.out.extend(on_disk_nodes.as_bytes()); |
|
628 | self.out.extend(on_disk_nodes.as_bytes()); | |
624 | Ok(ChildNodes { start, len }) |
|
629 | Ok(ChildNodes { start, len }) | |
625 | } |
|
630 | } | |
626 |
|
631 | |||
627 | /// If the given slice of items is within `on_disk`, returns its offset |
|
632 | /// If the given slice of items is within `on_disk`, returns its offset | |
628 | /// from the start of `on_disk`. |
|
633 | /// from the start of `on_disk`. | |
629 | fn on_disk_offset_of<T>(&self, slice: &[T]) -> Option<Offset> |
|
634 | fn on_disk_offset_of<T>(&self, slice: &[T]) -> Option<Offset> | |
630 | where |
|
635 | where | |
631 | T: BytesCast, |
|
636 | T: BytesCast, | |
632 | { |
|
637 | { | |
633 | fn address_range(slice: &[u8]) -> std::ops::RangeInclusive<usize> { |
|
638 | fn address_range(slice: &[u8]) -> std::ops::RangeInclusive<usize> { | |
634 | let start = slice.as_ptr() as usize; |
|
639 | let start = slice.as_ptr() as usize; | |
635 | let end = start + slice.len(); |
|
640 | let end = start + slice.len(); | |
636 | start..=end |
|
641 | start..=end | |
637 | } |
|
642 | } | |
638 | let slice_addresses = address_range(slice.as_bytes()); |
|
643 | let slice_addresses = address_range(slice.as_bytes()); | |
639 | let on_disk_addresses = address_range(self.dirstate_map.on_disk); |
|
644 | let on_disk_addresses = address_range(self.dirstate_map.on_disk); | |
640 | if on_disk_addresses.contains(slice_addresses.start()) |
|
645 | if on_disk_addresses.contains(slice_addresses.start()) | |
641 | && on_disk_addresses.contains(slice_addresses.end()) |
|
646 | && on_disk_addresses.contains(slice_addresses.end()) | |
642 | { |
|
647 | { | |
643 | let offset = slice_addresses.start() - on_disk_addresses.start(); |
|
648 | let offset = slice_addresses.start() - on_disk_addresses.start(); | |
644 | Some(offset_from_usize(offset)) |
|
649 | Some(offset_from_usize(offset)) | |
645 | } else { |
|
650 | } else { | |
646 | None |
|
651 | None | |
647 | } |
|
652 | } | |
648 | } |
|
653 | } | |
649 |
|
654 | |||
650 | fn current_offset(&mut self) -> Offset { |
|
655 | fn current_offset(&mut self) -> Offset { | |
651 | let mut offset = self.out.len(); |
|
656 | let mut offset = self.out.len(); | |
652 | if self.append { |
|
657 | if self.append { | |
653 | offset += self.dirstate_map.on_disk.len() |
|
658 | offset += self.dirstate_map.on_disk.len() | |
654 | } |
|
659 | } | |
655 | offset_from_usize(offset) |
|
660 | offset_from_usize(offset) | |
656 | } |
|
661 | } | |
657 |
|
662 | |||
658 | fn write_path(&mut self, slice: &[u8]) -> PathSlice { |
|
663 | fn write_path(&mut self, slice: &[u8]) -> PathSlice { | |
659 | let len = path_len_from_usize(slice.len()); |
|
664 | let len = path_len_from_usize(slice.len()); | |
660 | // Reuse an already-written path if possible |
|
665 | // Reuse an already-written path if possible | |
661 | if self.append { |
|
666 | if self.append { | |
662 | if let Some(start) = self.on_disk_offset_of(slice) { |
|
667 | if let Some(start) = self.on_disk_offset_of(slice) { | |
663 | return PathSlice { start, len }; |
|
668 | return PathSlice { start, len }; | |
664 | } |
|
669 | } | |
665 | } |
|
670 | } | |
666 | let start = self.current_offset(); |
|
671 | let start = self.current_offset(); | |
667 | self.out.extend(slice.as_bytes()); |
|
672 | self.out.extend(slice.as_bytes()); | |
668 | PathSlice { start, len } |
|
673 | PathSlice { start, len } | |
669 | } |
|
674 | } | |
670 | } |
|
675 | } | |
671 |
|
676 | |||
672 | fn offset_from_usize(x: usize) -> Offset { |
|
677 | fn offset_from_usize(x: usize) -> Offset { | |
673 | u32::try_from(x) |
|
678 | u32::try_from(x) | |
674 | // Could only panic for a dirstate file larger than 4 GiB |
|
679 | // Could only panic for a dirstate file larger than 4 GiB | |
675 | .expect("dirstate-v2 offset overflow") |
|
680 | .expect("dirstate-v2 offset overflow") | |
676 | .into() |
|
681 | .into() | |
677 | } |
|
682 | } | |
678 |
|
683 | |||
679 | fn child_nodes_len_from_usize(x: usize) -> Size { |
|
684 | fn child_nodes_len_from_usize(x: usize) -> Size { | |
680 | u32::try_from(x) |
|
685 | u32::try_from(x) | |
681 | // Could only panic with over 4 billion nodes |
|
686 | // Could only panic with over 4 billion nodes | |
682 | .expect("dirstate-v2 slice length overflow") |
|
687 | .expect("dirstate-v2 slice length overflow") | |
683 | .into() |
|
688 | .into() | |
684 | } |
|
689 | } | |
685 |
|
690 | |||
686 | fn path_len_from_usize(x: usize) -> PathSize { |
|
691 | fn path_len_from_usize(x: usize) -> PathSize { | |
687 | u16::try_from(x) |
|
692 | u16::try_from(x) | |
688 | // Could only panic for paths over 64 KiB |
|
693 | // Could only panic for paths over 64 KiB | |
689 | .expect("dirstate-v2 path length overflow") |
|
694 | .expect("dirstate-v2 path length overflow") | |
690 | .into() |
|
695 | .into() | |
691 | } |
|
696 | } | |
692 |
|
697 | |||
693 | impl From<TruncatedTimestamp> for PackedTruncatedTimestamp { |
|
698 | impl From<TruncatedTimestamp> for PackedTruncatedTimestamp { | |
694 | fn from(timestamp: TruncatedTimestamp) -> Self { |
|
699 | fn from(timestamp: TruncatedTimestamp) -> Self { | |
695 | Self { |
|
700 | Self { | |
696 | truncated_seconds: timestamp.truncated_seconds().into(), |
|
701 | truncated_seconds: timestamp.truncated_seconds().into(), | |
697 | nanoseconds: timestamp.nanoseconds().into(), |
|
702 | nanoseconds: timestamp.nanoseconds().into(), | |
698 | } |
|
703 | } | |
699 | } |
|
704 | } | |
700 | } |
|
705 | } | |
701 |
|
706 | |||
702 | impl TryFrom<PackedTruncatedTimestamp> for TruncatedTimestamp { |
|
707 | impl TryFrom<PackedTruncatedTimestamp> for TruncatedTimestamp { | |
703 | type Error = DirstateV2ParseError; |
|
708 | type Error = DirstateV2ParseError; | |
704 |
|
709 | |||
705 | fn try_from( |
|
710 | fn try_from( | |
706 | timestamp: PackedTruncatedTimestamp, |
|
711 | timestamp: PackedTruncatedTimestamp, | |
707 | ) -> Result<Self, Self::Error> { |
|
712 | ) -> Result<Self, Self::Error> { | |
708 | Self::from_already_truncated( |
|
713 | Self::from_already_truncated( | |
709 | timestamp.truncated_seconds.get(), |
|
714 | timestamp.truncated_seconds.get(), | |
710 | timestamp.nanoseconds.get(), |
|
715 | timestamp.nanoseconds.get(), | |
711 | ) |
|
716 | ) | |
712 | } |
|
717 | } | |
713 | } |
|
718 | } | |
714 | impl PackedTruncatedTimestamp { |
|
719 | impl PackedTruncatedTimestamp { | |
715 | fn null() -> Self { |
|
720 | fn null() -> Self { | |
716 | Self { |
|
721 | Self { | |
717 | truncated_seconds: 0.into(), |
|
722 | truncated_seconds: 0.into(), | |
718 | nanoseconds: 0.into(), |
|
723 | nanoseconds: 0.into(), | |
719 | } |
|
724 | } | |
720 | } |
|
725 | } | |
721 | } |
|
726 | } |
General Comments 0
You need to be logged in to leave comments.
Login now