rustpython-stdlib 0.6.0

RustPython standard libraries in Rust.
Documentation
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
// spell-checker:ignore ARMTHUMB memlimit

pub(crate) use _lzma::module_def;

#[pymodule]
mod _lzma {
    use crate::compression::DecompressorArgs;
    use alloc::fmt;
    use core::sync::atomic::{AtomicBool, AtomicI32, Ordering};
    use rustpython_common::{compression::lzma as backend, lock::PyMutex};
    use rustpython_vm::builtins::{PyBaseExceptionRef, PyBytes, PyDict, PyType, PyTypeRef};
    use rustpython_vm::function::{ArgBytesLike, ItemDoc};
    use rustpython_vm::object::PyAtomicRef;
    use rustpython_vm::types::Constructor;
    use rustpython_vm::{Py, PyObject, PyObjectRef, PyPayload, PyResult, VirtualMachine};

    #[pyattr]
    const CHECK_NONE: i32 = backend::CHECK_NONE;
    #[pyattr]
    const CHECK_CRC32: i32 = backend::CHECK_CRC32;
    #[pyattr]
    const CHECK_CRC64: i32 = backend::CHECK_CRC64;
    #[pyattr]
    const CHECK_SHA256: i32 = backend::CHECK_SHA256;
    #[pyattr]
    const CHECK_ID_MAX: i32 = backend::CHECK_ID_MAX;
    #[pyattr]
    const CHECK_UNKNOWN: i32 = backend::CHECK_UNKNOWN;

    #[pyattr]
    const MF_HC3: i32 = backend::MF_HC3;
    #[pyattr]
    const MF_HC4: i32 = backend::MF_HC4;
    #[pyattr]
    const MF_BT2: i32 = backend::MF_BT2;
    #[pyattr]
    const MF_BT3: i32 = backend::MF_BT3;
    #[pyattr]
    const MF_BT4: i32 = backend::MF_BT4;

    #[pyattr]
    const MODE_FAST: i32 = backend::MODE_FAST;
    #[pyattr]
    const MODE_NORMAL: i32 = backend::MODE_NORMAL;

    #[pyattr]
    const FORMAT_AUTO: i32 = backend::FORMAT_AUTO;
    #[pyattr]
    const FORMAT_XZ: i32 = backend::FORMAT_XZ;
    #[pyattr]
    const FORMAT_ALONE: i32 = backend::FORMAT_ALONE;
    #[pyattr]
    const FORMAT_RAW: i32 = backend::FORMAT_RAW;

    #[pyattr]
    const FILTER_LZMA1: u64 = backend::FILTER_LZMA1;
    #[pyattr]
    const FILTER_LZMA2: u64 = backend::FILTER_LZMA2;
    #[pyattr]
    const FILTER_DELTA: u64 = backend::FILTER_DELTA;
    #[pyattr]
    const FILTER_X86: u64 = backend::FILTER_X86;
    #[pyattr]
    const FILTER_POWERPC: u64 = backend::FILTER_POWERPC;
    #[pyattr]
    const FILTER_IA64: u64 = backend::FILTER_IA64;
    #[pyattr]
    const FILTER_ARM: u64 = backend::FILTER_ARM;
    #[pyattr]
    const FILTER_ARMTHUMB: u64 = backend::FILTER_ARMTHUMB;
    #[pyattr]
    const FILTER_SPARC: u64 = backend::FILTER_SPARC;

    #[pyattr]
    const PRESET_DEFAULT: u32 = backend::PRESET_DEFAULT;
    #[pyattr]
    const PRESET_EXTREME: u32 = backend::PRESET_EXTREME;

    #[pyattr(once, name = "LZMAError")]
    fn error(vm: &VirtualMachine) -> PyTypeRef {
        vm.ctx.new_exception_type_with_doc(
            "_lzma",
            "LZMAError",
            Some(vec![vm.ctx.exceptions.exception_type.to_owned()]),
            const { ItemDoc::db("_lzma.LZMAError") },
        )
    }

    fn new_lzma_error(message: impl Into<String>, vm: &VirtualMachine) -> PyBaseExceptionRef {
        let message: String = message.into();
        vm.new_exception_msg(vm.class("lzma", "LZMAError"), message.into())
    }

    fn map_backend_error(error: backend::Error, vm: &VirtualMachine) -> PyBaseExceptionRef {
        match error {
            backend::Error::Memory => vm.no_memory_error(),
            backend::Error::Value(message) => vm.new_value_error(message),
            backend::Error::Lzma(message) => new_lzma_error(message, vm),
            backend::Error::Eof => vm.new_eof_error("End of stream already reached"),
        }
    }

    fn get_dict_opt_u32(spec: &PyObject, key: &str, vm: &VirtualMachine) -> PyResult<Option<u32>> {
        let dict = spec.downcast_ref::<PyDict>().ok_or_else(|| {
            vm.new_type_error("Filter specifier must be a dict or dict-like object")
        })?;
        match dict.get_item_opt(key, vm)? {
            Some(value) => Ok(Some(value.try_into_value::<u32>(vm)?)),
            None => Ok(None),
        }
    }

    fn get_dict_opt_u64(spec: &PyObject, key: &str, vm: &VirtualMachine) -> PyResult<Option<u64>> {
        let dict = spec.downcast_ref::<PyDict>().ok_or_else(|| {
            vm.new_type_error("Filter specifier must be a dict or dict-like object")
        })?;
        match dict.get_item_opt(key, vm)? {
            Some(value) => Ok(Some(value.try_into_value::<u64>(vm)?)),
            None => Ok(None),
        }
    }

    fn filter_spec_with_id(spec: &PyObject, vm: &VirtualMachine) -> PyResult<backend::FilterSpec> {
        let id = get_dict_opt_u64(spec, "id", vm)?
            .ok_or_else(|| vm.new_value_error("Filter specifier must have an \"id\" entry"))?;
        Ok(backend::FilterSpec {
            id,
            ..backend::FilterSpec::default()
        })
    }

    fn parse_filter_chain_item(
        spec: &PyObject,
        vm: &VirtualMachine,
    ) -> PyResult<backend::FilterSpec> {
        let mut parsed = filter_spec_with_id(spec, vm)?;
        match parsed.id {
            FILTER_LZMA1 | FILTER_LZMA2 => {
                parsed.preset = get_dict_opt_u32(spec, "preset", vm)?;
                parsed.dict_size = get_dict_opt_u32(spec, "dict_size", vm)?;
                parsed.lc = get_dict_opt_u32(spec, "lc", vm)?;
                parsed.lp = get_dict_opt_u32(spec, "lp", vm)?;
                parsed.pb = get_dict_opt_u32(spec, "pb", vm)?;
                parsed.mode = get_dict_opt_u32(spec, "mode", vm)?;
                parsed.nice_len = get_dict_opt_u32(spec, "nice_len", vm)?;
                parsed.mf = get_dict_opt_u32(spec, "mf", vm)?;
                parsed.depth = get_dict_opt_u32(spec, "depth", vm)?;
            }
            FILTER_DELTA => parsed.dist = get_dict_opt_u32(spec, "dist", vm)?,
            FILTER_X86 | FILTER_POWERPC | FILTER_IA64 | FILTER_ARM | FILTER_ARMTHUMB
            | FILTER_SPARC => {
                parsed.start_offset = get_dict_opt_u32(spec, "start_offset", vm)?;
            }
            _ => {}
        }
        Ok(parsed)
    }

    fn parse_filter_properties(
        spec: &PyObject,
        vm: &VirtualMachine,
    ) -> PyResult<backend::FilterSpec> {
        let mut parsed = filter_spec_with_id(spec, vm)?;
        match parsed.id {
            FILTER_LZMA1 => {
                parsed.preset = get_dict_opt_u32(spec, "preset", vm)?;
                parsed.lc = get_dict_opt_u32(spec, "lc", vm)?;
                parsed.lp = get_dict_opt_u32(spec, "lp", vm)?;
                parsed.pb = get_dict_opt_u32(spec, "pb", vm)?;
                parsed.dict_size = get_dict_opt_u32(spec, "dict_size", vm)?;
            }
            FILTER_LZMA2 => {
                parsed.preset = get_dict_opt_u32(spec, "preset", vm)?;
                parsed.dict_size = get_dict_opt_u32(spec, "dict_size", vm)?;
            }
            FILTER_DELTA => parsed.dist = get_dict_opt_u32(spec, "dist", vm)?,
            FILTER_X86 | FILTER_POWERPC | FILTER_IA64 | FILTER_ARM | FILTER_ARMTHUMB
            | FILTER_SPARC => {
                parsed.start_offset = get_dict_opt_u32(spec, "start_offset", vm)?;
            }
            _ => {}
        }
        Ok(parsed)
    }

    fn parse_filter_chain(
        filter_specs: &PyObject,
        vm: &VirtualMachine,
    ) -> PyResult<Vec<backend::FilterSpec>> {
        const LZMA_FILTERS_MAX: usize = 4;
        let length = filter_specs.length(vm)?;
        if length > LZMA_FILTERS_MAX {
            return Err(new_lzma_error(
                format!("Too many filters - liblzma supports a maximum of {LZMA_FILTERS_MAX}"),
                vm,
            ));
        }
        let sequence = filter_specs.try_sequence(vm)?;
        (0..length)
            .map(|index| {
                let spec = sequence.get_item(index as isize, vm)?;
                parse_filter_chain_item(&spec, vm)
            })
            .collect()
    }

    fn filters_to_backend(
        filters: Option<PyObjectRef>,
        vm: &VirtualMachine,
    ) -> PyResult<Option<Vec<backend::FilterSpec>>> {
        filters
            .map(|filters| parse_filter_chain(&filters, vm))
            .transpose()
    }

    fn filter_spec_to_dict(
        spec: backend::FilterSpec,
        vm: &VirtualMachine,
    ) -> PyResult<PyObjectRef> {
        let dict = vm.ctx.new_dict();
        dict.set_item("id", vm.new_pyobj(spec.id), vm)?;
        match spec.id {
            FILTER_LZMA1 => {
                dict.set_item("lc", vm.new_pyobj(spec.lc.unwrap()), vm)?;
                dict.set_item("lp", vm.new_pyobj(spec.lp.unwrap()), vm)?;
                dict.set_item("pb", vm.new_pyobj(spec.pb.unwrap()), vm)?;
                dict.set_item("dict_size", vm.new_pyobj(spec.dict_size.unwrap()), vm)?;
            }
            FILTER_LZMA2 => {
                dict.set_item("dict_size", vm.new_pyobj(spec.dict_size.unwrap()), vm)?;
            }
            FILTER_DELTA => {
                dict.set_item("dist", vm.new_pyobj(spec.dist.unwrap()), vm)?;
            }
            FILTER_X86 | FILTER_POWERPC | FILTER_IA64 | FILTER_ARM | FILTER_ARMTHUMB
            | FILTER_SPARC => {
                if let Some(start_offset) = spec.start_offset {
                    dict.set_item("start_offset", vm.new_pyobj(start_offset), vm)?;
                }
            }
            _ => unreachable!("common backend validated the filter ID"),
        }
        Ok(dict.into())
    }

    #[pyfunction]
    fn is_check_supported(check_id: i32) -> bool {
        backend::is_check_supported(check_id)
    }

    #[pyfunction]
    fn _encode_filter_properties(filter: PyObjectRef, vm: &VirtualMachine) -> PyResult<Vec<u8>> {
        let spec = parse_filter_properties(&filter, vm)?;
        backend::encode_filter_properties(&spec).map_err(|error| map_backend_error(error, vm))
    }

    #[pyfunction]
    fn _decode_filter_properties(
        filter_id: u64,
        encoded_props: ArgBytesLike,
        vm: &VirtualMachine,
    ) -> PyResult<PyObjectRef> {
        let spec = encoded_props
            .with_ref(|properties| backend::decode_filter_properties(filter_id, properties));
        filter_spec_to_dict(spec.map_err(|error| map_backend_error(error, vm))?, vm)
    }

    struct DecompressorInner {
        backend: backend::Decompressor,
    }

    #[pyattr]
    #[pyclass(name = "LZMADecompressor", traverse)]
    #[derive(PyPayload)]
    struct LZMADecompressor {
        #[pytraverse(skip)]
        state: PyMutex<DecompressorInner>,
        #[pymember]
        #[pytraverse(skip)]
        check: AtomicI32,
        #[pymember]
        #[pytraverse(skip)]
        eof: AtomicBool,
        #[pymember]
        #[pytraverse(skip)]
        needs_input: AtomicBool,
        #[pymember(type = "object_ex")]
        unused_data: PyAtomicRef<Option<PyObject>>,
    }

    impl fmt::Debug for LZMADecompressor {
        fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
            write!(f, "_lzma.LZMADecompressor")
        }
    }

    #[derive(FromArgs)]
    pub(super) struct LZMADecompressorConstructorArgs {
        #[pyarg(any, default = ::FORMAT_AUTO)]
        format: i32,
        #[pyarg(any, optional)]
        memlimit: Option<u64>,
        #[pyarg(any, optional)]
        filters: Option<PyObjectRef>,
    }

    impl Constructor for LZMADecompressor {
        type Args = LZMADecompressorConstructorArgs;

        fn py_new(_cls: &Py<PyType>, args: Self::Args, vm: &VirtualMachine) -> PyResult<Self> {
            if args.format == FORMAT_RAW && args.memlimit.is_some() {
                return Err(vm.new_value_error("Cannot specify memory limit with FORMAT_RAW"));
            }
            if args.format == FORMAT_RAW && args.filters.is_none() {
                return Err(vm.new_value_error("Must specify filters for FORMAT_RAW"));
            }
            if args.format != FORMAT_RAW && args.filters.is_some() {
                return Err(vm.new_value_error("Cannot specify filters except with FORMAT_RAW"));
            }
            let filters = filters_to_backend(args.filters, vm)?;
            let backend = backend::Decompressor::new(args.format, args.memlimit, filters)
                .map_err(|error| map_backend_error(error, vm))?;
            let check = backend.check();
            Ok(Self {
                state: PyMutex::new(DecompressorInner { backend }),
                check: AtomicI32::new(check),
                eof: AtomicBool::new(false),
                needs_input: AtomicBool::new(true),
                unused_data: PyAtomicRef::from(Some(vm.ctx.empty_bytes.clone().into())),
            })
        }
    }

    #[pyclass(with(Constructor))]
    impl LZMADecompressor {
        #[pymethod]
        fn decompress(
            zelf: &Py<Self>,
            args: DecompressorArgs,
            vm: &VirtualMachine,
        ) -> PyResult<Vec<u8>> {
            let max_length = args.max_length();
            let data = &*args.data();
            let mut state = zelf.state.lock();
            let result = state.backend.decompress(data, max_length);
            zelf.check.store(state.backend.check(), Ordering::Relaxed);
            zelf.eof.store(state.backend.eof(), Ordering::Relaxed);
            zelf.needs_input
                .store(state.backend.needs_input(), Ordering::Relaxed);
            let stale = zelf.unused_data.deref().is_none_or(|obj| {
                obj.downcast_ref::<PyBytes>()
                    .is_none_or(|bytes| bytes.as_bytes() != state.backend.unused_data())
            });
            if stale {
                let bytes = vm.ctx.new_bytes(state.backend.unused_data().to_vec());
                let _previous = unsafe { zelf.unused_data.swap(Some(bytes.into())) };
            }
            result.map_err(|error| map_backend_error(error, vm))
        }
    }

    #[pyattr]
    #[pyclass(name = "LZMACompressor")]
    #[derive(PyPayload)]
    struct LZMACompressor {
        state: PyMutex<backend::Compressor>,
    }

    impl fmt::Debug for LZMACompressor {
        fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
            write!(f, "_lzma.LZMACompressor")
        }
    }

    #[derive(FromArgs)]
    pub(super) struct LZMACompressorConstructorArgs {
        #[pyarg(any, default = ::FORMAT_XZ)]
        format: i32,
        #[pyarg(any, default = -1)]
        check: i32,
        #[pyarg(any, optional)]
        preset: Option<PyObjectRef>,
        #[pyarg(any, optional)]
        filters: Option<PyObjectRef>,
    }

    impl Constructor for LZMACompressor {
        type Args = LZMACompressorConstructorArgs;

        fn py_new(_cls: &Py<PyType>, args: Self::Args, vm: &VirtualMachine) -> PyResult<Self> {
            if args.format != FORMAT_XZ && args.check != -1 && args.check != CHECK_NONE {
                return Err(new_lzma_error(
                    "Integrity checks are only supported by FORMAT_XZ",
                    vm,
                ));
            }
            if args.preset.is_some() && args.filters.is_some() {
                return Err(new_lzma_error(
                    "Cannot specify both preset and filter chain",
                    vm,
                ));
            }
            let preset = match args.preset {
                Some(preset) => preset.try_into_value::<u32>(vm)?,
                None => PRESET_DEFAULT,
            };
            let filters = match args.format {
                FORMAT_XZ | FORMAT_ALONE | FORMAT_RAW => filters_to_backend(args.filters, vm)?,
                _ => None,
            };
            let backend = backend::Compressor::new(args.format, args.check, preset, filters)
                .map_err(|error| map_backend_error(error, vm))?;
            Ok(Self {
                state: PyMutex::new(backend),
            })
        }
    }

    #[pyclass(with(Constructor))]
    impl LZMACompressor {
        #[pymethod]
        fn compress(zelf: &Py<Self>, data: ArgBytesLike, vm: &VirtualMachine) -> PyResult<Vec<u8>> {
            data.with_ref(|data| zelf.state.lock().compress(data))
                .map_err(|error| map_backend_error(error, vm))
        }

        #[pymethod]
        fn flush(zelf: &Py<Self>, vm: &VirtualMachine) -> PyResult<Vec<u8>> {
            zelf.state
                .lock()
                .flush()
                .map_err(|error| map_backend_error(error, vm))
        }
    }
}