/*
read_directory(archive) -> files dict (new reference)
Given a path to a Zip archive, build a dict, mapping file names
(local to the archive, using SEP as a separator) to toc entries.
A toc_entry is a tuple:
(__file__, # value to use for __file__, available for all files
compress, # compression kind; 0 for uncompressed
data_size, # size of compressed data on disk
file_size, # size of decompressed data
file_offset, # offset of file header from start of archive
time, # mod time of file (in dos format)
date, # mod data of file (in dos format)
crc, # crc checksum of the data
)
Directories can be recognized by the trailing SEP in the name,
data_size and file_offset are 0.
*/
static PyObject *
read_directory(char *archive)
{
PyObject *files = NULL;
FILE *fp;
long compress, crc, data_size, file_size, file_offset, date, time;
long header_offset, name_size, header_size, header_position;
long i, l, count;
size_t length;
char path[MAXPATHLEN + 5];
char name[MAXPATHLEN + 5];
char *p, endof_central_dir[22];
long arc_offset; /* offset from beginning of file to start of zip-archive */
if (strlen(archive) > MAXPATHLEN) {
PyErr_SetString(PyExc_OverflowError,
"Zip path name is too long");
return NULL;
}
strcpy(path, archive);
fp = fopen(archive, "rb");
if (fp == NULL) {
PyErr_Format(ZipImportError, "can't open Zip file: "
"'%.200s'", archive);
return NULL;
}
fseek(fp, -22, SEEK_END);
header_position = ftell(fp);
if (fread(endof_central_dir, 1, 22, fp) != 22) {
fclose(fp);
PyErr_Format(ZipImportError, "can't read Zip file: "
"'%.200s'", archive);
return NULL;
}
if (get_long((unsigned char *)endof_central_dir) != 0x06054B50) {
/* Bad: End of Central Dir signature */
fclose(fp);
PyErr_Format(ZipImportError, "not a Zip file: "
"'%.200s'", archive);
return NULL;
}
header_size = get_long((unsigned char *)endof_central_dir + 12);
header_offset = get_long((unsigned char *)endof_central_dir + 16);
arc_offset = header_position - header_offset - header_size;
header_offset += arc_offset;
files = PyDict_New();
if (files == NULL)
goto error;
length = (long)strlen(path);
path[length] = SEP;
/* Start of Central Directory */
count = 0;
for (;;) {
PyObject *t;
int err;
fseek(fp, header_offset, 0); /* Start of file header */
l = PyMarshal_ReadLongFromFile(fp);
if (l != 0x02014B50)
break; /* Bad: Central Dir File Header */
fseek(fp, header_offset + 10, 0);
compress = PyMarshal_ReadShortFromFile(fp);
time = PyMarshal_ReadShortFromFile(fp);
date = PyMarshal_ReadShortFromFile(fp);
crc = PyMarshal_ReadLongFromFile(fp);
data_size = PyMarshal_ReadLongFromFile(fp);
file_size = PyMarshal_ReadLongFromFile(fp);
name_size = PyMarshal_ReadShortFromFile(fp);
header_size = 46 + name_size +
PyMarshal_ReadShortFromFile(fp) +
PyMarshal_ReadShortFromFile(fp);
fseek(fp, header_offset + 42, 0);
file_offset = PyMarshal_ReadLongFromFile(fp) + arc_offset;
if (name_size > MAXPATHLEN)
name_size = MAXPATHLEN;
p = name;
for (i = 0; i < name_size; i++) {
*p = (char)getc(fp);
if (*p == '/')
*p = SEP;
p++;
}
*p = 0; /* Add terminating null byte */
header_offset += header_size;
strncpy(path + length + 1, name, MAXPATHLEN - length - 1);
t = Py_BuildValue("siiiiiii", path, compress, data_size,
file_size, file_offset, time, date, crc);
if (t == NULL)
goto error;
err = PyDict_SetItemString(files, name, t);
Py_DECREF(t);
if (err != 0)
goto error;
count++;
}
fclose(fp);
if (Py_VerboseFlag)
PySys_WriteStderr("# zipimport: found %ld names in %s\n",
count, archive);
return files;
error:
fclose(fp);
Py_XDECREF(files);
return NULL;
}
/* Given a path to a Zip file and a toc_entry, return the (uncompressed)
data as a new reference. */
static PyObject *
get_data(char *archive, PyObject *toc_entry)
{
PyObject *raw_data, *data = NULL, *decompress;
char *buf;
FILE *fp;
int err;
Py_ssize_t bytes_read = 0;
long l;
char *datapath;
long compress, data_size, file_size, file_offset;
long time, date, crc;
if (!PyArg_ParseTuple(toc_entry, "slllllll", &datapath, &compress,
&data_size, &file_size, &file_offset, &time,
&date, &crc)) {
return NULL;
}
fp = fopen(archive, "rb");
if (!fp) {
PyErr_Format(PyExc_IOError,
"zipimport: can not open file %s", archive);
return NULL;
}
/* Check to make sure the local file header is correct */
fseek(fp, file_offset, 0);
l = PyMarshal_ReadLongFromFile(fp);
if (l != 0x04034B50) {
/* Bad: Local File Header */
PyErr_Format(ZipImportError,
"bad local file header in %s",
archive);
fclose(fp);
return NULL;
}
fseek(fp, file_offset + 26, 0);
l = 30 + PyMarshal_ReadShortFromFile(fp) +
PyMarshal_ReadShortFromFile(fp); /* local header size */
file_offset += l; /* Start of file data */
raw_data = PyString_FromStringAndSize((char *)NULL, compress == 0 ?
data_size : data_size + 1);
if (raw_data == NULL) {
fclose(fp);
return NULL;
}
buf = PyString_AsString(raw_data);
err = fseek(fp, file_offset, 0);
if (err == 0)
bytes_read = fread(buf, 1, data_size, fp);
fclose(fp);
if (err || bytes_read != data_size) {
PyErr_SetString(PyExc_IOError,
"zipimport: can't read data");
Py_DECREF(raw_data);
return NULL;
}
if (compress != 0) {
buf[data_size] = 'Z'; /* saw this in zipfile.py */
data_size++;
}
buf[data_size] = '\0';
if (compress == 0) /* data is not compressed */
return raw_data;
/* Decompress with zlib */
decompress = get_decompress_func();
if (decompress == NULL) {
PyErr_SetString(ZipImportError,
"can't decompress data; "
"zlib not available");
goto error;
}
data = PyObject_CallFunction(decompress, "Oi", raw_data, -15);
error:
Py_DECREF(raw_data);
return data;
}
/*
read_directory(archive) -> files dict (new reference)
Given a path to a Zip archive, build a dict, mapping file names
(local to the archive, using SEP as a separator) to toc entries.
A toc_entry is a tuple:
(__file__, # value to use for __file__, available for all files,
# encoded to the filesystem encoding
compress, # compression kind; 0 for uncompressed
data_size, # size of compressed data on disk
file_size, # size of decompressed data
file_offset, # offset of file header from start of archive
time, # mod time of file (in dos format)
date, # mod data of file (in dos format)
crc, # crc checksum of the data
)
Directories can be recognized by the trailing SEP in the name,
data_size and file_offset are 0.
*/
static PyObject *
read_directory(PyObject *archive)
{
PyObject *files = NULL;
FILE *fp;
unsigned short flags;
short compress, time, date, name_size;
long crc, data_size, file_size, header_size;
Py_ssize_t file_offset, header_position, header_offset;
long l, count;
Py_ssize_t i;
char name[MAXPATHLEN + 5];
PyObject *nameobj = NULL;
char *p, endof_central_dir[22];
Py_ssize_t arc_offset; /* Absolute offset to start of the zip-archive. */
PyObject *path;
const char *charset;
int bootstrap;
fp = _Py_fopen(archive, "rb");
if (fp == NULL) {
if (!PyErr_Occurred())
PyErr_Format(ZipImportError, "can't open Zip file: %R", archive);
return NULL;
}
fseek(fp, -22, SEEK_END);
header_position = ftell(fp);
if (fread(endof_central_dir, 1, 22, fp) != 22) {
fclose(fp);
PyErr_Format(ZipImportError, "can't read Zip file: %R", archive);
return NULL;
}
if (get_long((unsigned char *)endof_central_dir) != 0x06054B50) {
/* Bad: End of Central Dir signature */
fclose(fp);
PyErr_Format(ZipImportError, "not a Zip file: %R", archive);
return NULL;
}
header_size = get_long((unsigned char *)endof_central_dir + 12);
header_offset = get_long((unsigned char *)endof_central_dir + 16);
arc_offset = header_position - header_offset - header_size;
header_offset += arc_offset;
files = PyDict_New();
if (files == NULL)
goto error;
/* Start of Central Directory */
count = 0;
for (;;) {
PyObject *t;
int err;
fseek(fp, header_offset, 0); /* Start of file header */
l = PyMarshal_ReadLongFromFile(fp);
if (l != 0x02014B50)
break; /* Bad: Central Dir File Header */
fseek(fp, header_offset + 8, 0);
flags = (unsigned short)PyMarshal_ReadShortFromFile(fp);
compress = PyMarshal_ReadShortFromFile(fp);
time = PyMarshal_ReadShortFromFile(fp);
date = PyMarshal_ReadShortFromFile(fp);
crc = PyMarshal_ReadLongFromFile(fp);
data_size = PyMarshal_ReadLongFromFile(fp);
file_size = PyMarshal_ReadLongFromFile(fp);
name_size = PyMarshal_ReadShortFromFile(fp);
header_size = 46 + name_size +
PyMarshal_ReadShortFromFile(fp) +
PyMarshal_ReadShortFromFile(fp);
fseek(fp, header_offset + 42, 0);
file_offset = PyMarshal_ReadLongFromFile(fp) + arc_offset;
if (name_size > MAXPATHLEN)
name_size = MAXPATHLEN;
p = name;
for (i = 0; i < (Py_ssize_t)name_size; i++) {
*p = (char)getc(fp);
if (*p == '/')
*p = SEP;
p++;
}
*p = 0; /* Add terminating null byte */
header_offset += header_size;
bootstrap = 0;
if (flags & 0x0800)
charset = "utf-8";
else if (!PyThreadState_GET()->interp->codecs_initialized) {
/* During bootstrap, we may need to load the encodings
package from a ZIP file. But the cp437 encoding is implemented
in Python in the encodings package.
Break out of this dependency by assuming that the path to
the encodings module is ASCII-only. */
charset = "ascii";
bootstrap = 1;
}
else
charset = "cp437";
nameobj = PyUnicode_Decode(name, name_size, charset, NULL);
if (PyUnicode_READY(nameobj) == -1)
goto error;
if (nameobj == NULL) {
if (bootstrap)
PyErr_Format(PyExc_NotImplementedError,
"bootstrap issue: python%i%i.zip contains non-ASCII "
"filenames without the unicode flag",
PY_MAJOR_VERSION, PY_MINOR_VERSION);
goto error;
}
path = PyUnicode_FromFormat("%U%c%U", archive, SEP, nameobj);
if (path == NULL)
goto error;
t = Py_BuildValue("Nhllnhhl", path, compress, data_size,
file_size, file_offset, time, date, crc);
if (t == NULL)
goto error;
err = PyDict_SetItem(files, nameobj, t);
Py_CLEAR(nameobj);
Py_DECREF(t);
if (err != 0)
goto error;
count++;
}
fclose(fp);
if (Py_VerboseFlag)
PySys_FormatStderr("# zipimport: found %ld names in %R\n",
count, archive);
return files;
error:
fclose(fp);
Py_XDECREF(files);
Py_XDECREF(nameobj);
return NULL;
}
