From 7c4b6a68f263320a2dd19cd5ff63b35c964b1fa8 Mon Sep 17 00:00:00 2001 From: Alyssa Coghlan Date: Tue, 8 Oct 2024 18:34:11 +1000 Subject: bpo-34206: Improve docs and test coverage for pre-init functions (#8023) - move the Py_Main documentation from the very high level API section to the initialization and finalization section - make it clear that it encapsulates a full Py_Initialize/Finalize cycle of its own - point out that exactly which settings will be read and applied correctly when Py_Main is called after a separate runtime initialization call is version dependent - be explicit that Py_IsInitialized can be called prior to initialization - actually test that Py_IsInitialized can be called prior to initialization - flush stdout in the embedding tests that run code so it appears in the expected order when running with "-vv" - make "-vv" on the subinterpreter embedding tests less spammy --------- Co-authored-by: Carol Willing --- Doc/c-api/init.rst | 162 ++++++++++++++++++--- Doc/c-api/init_config.rst | 29 +--- Doc/c-api/veryhigh.rst | 24 --- Lib/test/test_embed.py | 11 +- .../C API/2018-06-30-21-48-16.bpo-34008.2Wjtm0.rst | 2 + .../2018-07-04-20-35-25.bpo-34008.bqecIb.rst | 8 + Programs/_testembed.c | 41 +++++- 7 files changed, 199 insertions(+), 78 deletions(-) create mode 100644 Misc/NEWS.d/next/C API/2018-06-30-21-48-16.bpo-34008.2Wjtm0.rst create mode 100644 Misc/NEWS.d/next/Documentation/2018-07-04-20-35-25.bpo-34008.bqecIb.rst diff --git a/Doc/c-api/init.rst b/Doc/c-api/init.rst index 6d16e04..8e0cf7bb 100644 --- a/Doc/c-api/init.rst +++ b/Doc/c-api/init.rst @@ -7,7 +7,8 @@ Initialization, Finalization, and Threads ***************************************** -See also the :ref:`Python Initialization Configuration `. +See :ref:`Python Initialization Configuration ` for details +on how to configure the interpreter prior to initialization. .. _pre-init-safe: @@ -21,6 +22,15 @@ a few functions and the :ref:`global configuration variables The following functions can be safely called before Python is initialized: +* Functions that initialize the interpreter: + + * :c:func:`Py_Initialize` + * :c:func:`Py_InitializeEx` + * :c:func:`Py_InitializeFromConfig` + * :c:func:`Py_BytesMain` + * :c:func:`Py_Main` + * the runtime pre-initialization functions covered in :ref:`init-config` + * Configuration functions: * :c:func:`PyImport_AppendInittab` @@ -32,6 +42,7 @@ The following functions can be safely called before Python is initialized: * :c:func:`Py_SetProgramName` * :c:func:`Py_SetPythonHome` * :c:func:`PySys_ResetWarnOptions` + * the configuration functions covered in :ref:`init-config` * Informative functions: @@ -43,10 +54,12 @@ The following functions can be safely called before Python is initialized: * :c:func:`Py_GetCopyright` * :c:func:`Py_GetPlatform` * :c:func:`Py_GetVersion` + * :c:func:`Py_IsInitialized` * Utilities: * :c:func:`Py_DecodeLocale` + * the status reporting and utility functions covered in :ref:`init-config` * Memory allocators: @@ -62,11 +75,13 @@ The following functions can be safely called before Python is initialized: .. note:: - The following functions **should not be called** before - :c:func:`Py_Initialize`: :c:func:`Py_EncodeLocale`, :c:func:`Py_GetPath`, + Despite their apparent similarity to some of the functions listed above, + the following functions **should not be called** before the interpreter has + been initialized: :c:func:`Py_EncodeLocale`, :c:func:`Py_GetPath`, :c:func:`Py_GetPrefix`, :c:func:`Py_GetExecPrefix`, :c:func:`Py_GetProgramFullPath`, :c:func:`Py_GetPythonHome`, - :c:func:`Py_GetProgramName` and :c:func:`PyEval_InitThreads`. + :c:func:`Py_GetProgramName`, :c:func:`PyEval_InitThreads`, and + :c:func:`Py_RunMain`. .. _global-conf-vars: @@ -346,34 +361,42 @@ Initializing and finalizing the interpreter this should be called before using any other Python/C API functions; see :ref:`Before Python Initialization ` for the few exceptions. - This initializes - the table of loaded modules (``sys.modules``), and creates the fundamental - modules :mod:`builtins`, :mod:`__main__` and :mod:`sys`. It also initializes - the module search path (``sys.path``). It does not set ``sys.argv``; use - the new :c:type:`PyConfig` API of the :ref:`Python Initialization - Configuration ` for that. This is a no-op when called for a - second time - (without calling :c:func:`Py_FinalizeEx` first). There is no return value; it is a - fatal error if the initialization fails. - - Use the :c:func:`Py_InitializeFromConfig` function to customize the + This initializes the table of loaded modules (``sys.modules``), and creates + the fundamental modules :mod:`builtins`, :mod:`__main__` and :mod:`sys`. + It also initializes the module search path (``sys.path``). It does not set + ``sys.argv``; use the :ref:`Python Initialization Configuration ` + API for that. This is a no-op when called for a second time (without calling + :c:func:`Py_FinalizeEx` first). There is no return value; it is a fatal + error if the initialization fails. + + Use :c:func:`Py_InitializeFromConfig` to customize the :ref:`Python Initialization Configuration `. .. note:: - On Windows, changes the console mode from ``O_TEXT`` to ``O_BINARY``, which will - also affect non-Python uses of the console using the C Runtime. + On Windows, changes the console mode from ``O_TEXT`` to ``O_BINARY``, + which will also affect non-Python uses of the console using the C Runtime. .. c:function:: void Py_InitializeEx(int initsigs) This function works like :c:func:`Py_Initialize` if *initsigs* is ``1``. If - *initsigs* is ``0``, it skips initialization registration of signal handlers, which - might be useful when Python is embedded. + *initsigs* is ``0``, it skips initialization registration of signal handlers, + which may be useful when CPython is embedded as part of a larger application. - Use the :c:func:`Py_InitializeFromConfig` function to customize the + Use :c:func:`Py_InitializeFromConfig` to customize the :ref:`Python Initialization Configuration `. +.. c:function:: PyStatus Py_InitializeFromConfig(const PyConfig *config) + + Initialize Python from *config* configuration, as described in + :ref:`init-from-config`. + + See the :ref:`init-config` section for details on pre-initializing the + interpreter, populating the runtime configuration structure, and querying + the returned status structure. + + .. c:function:: int Py_IsInitialized() Return true (nonzero) when the Python interpreter has been initialized, false @@ -440,12 +463,111 @@ Initializing and finalizing the interpreter .. versionadded:: 3.6 + .. c:function:: void Py_Finalize() This is a backwards-compatible version of :c:func:`Py_FinalizeEx` that disregards the return value. +.. c:function:: int Py_BytesMain(int argc, char **argv) + + Similar to :c:func:`Py_Main` but *argv* is an array of bytes strings, + allowing the calling application to delegate the text decoding step to + the CPython runtime. + + .. versionadded:: 3.8 + + +.. c:function:: int Py_Main(int argc, wchar_t **argv) + + The main program for the standard interpreter, encapsulating a full + initialization/finalization cycle, as well as additional + behaviour to implement reading configurations settings from the environment + and command line, and then executing ``__main__`` in accordance with + :ref:`using-on-cmdline`. + + This is made available for programs which wish to support the full CPython + command line interface, rather than just embedding a Python runtime in a + larger application. + + The *argc* and *argv* parameters are similar to those which are passed to a + C program's :c:func:`main` function, except that the *argv* entries are first + converted to ``wchar_t`` using :c:func:`Py_DecodeLocale`. It is also + important to note that the argument list entries may be modified to point to + strings other than those passed in (however, the contents of the strings + pointed to by the argument list are not modified). + + The return value will be ``0`` if the interpreter exits normally (i.e., + without an exception), ``1`` if the interpreter exits due to an exception, + or ``2`` if the argument list does not represent a valid Python command + line. + + Note that if an otherwise unhandled :exc:`SystemExit` is raised, this + function will not return ``1``, but exit the process, as long as + ``Py_InspectFlag`` is not set. If ``Py_InspectFlag`` is set, execution will + drop into the interactive Python prompt, at which point a second otherwise + unhandled :exc:`SystemExit` will still exit the process, while any other + means of exiting will set the return value as described above. + + In terms of the CPython runtime configuration APIs documented in the + :ref:`runtime configuration ` section (and without accounting + for error handling), ``Py_Main`` is approximately equivalent to:: + + PyConfig config; + PyConfig_InitPythonConfig(&config); + PyConfig_SetArgv(&config, argc, argv); + Py_InitializeFromConfig(&config); + PyConfig_Clear(&config); + + Py_RunMain(); + + In normal usage, an embedding application will call this function + *instead* of calling :c:func:`Py_Initialize`, :c:func:`Py_InitializeEx` or + :c:func:`Py_InitializeFromConfig` directly, and all settings will be applied + as described elsewhere in this documentation. If this function is instead + called *after* a preceding runtime initialization API call, then exactly + which environmental and command line configuration settings will be updated + is version dependent (as it depends on which settings correctly support + being modified after they have already been set once when the runtime was + first initialized). + + +.. c:function:: int Py_RunMain(void) + + Executes the main module in a fully configured CPython runtime. + + Executes the command (:c:member:`PyConfig.run_command`), the script + (:c:member:`PyConfig.run_filename`) or the module + (:c:member:`PyConfig.run_module`) specified on the command line or in the + configuration. If none of these values are set, runs the interactive Python + prompt (REPL) using the ``__main__`` module's global namespace. + + If :c:member:`PyConfig.inspect` is not set (the default), the return value + will be ``0`` if the interpreter exits normally (that is, without raising + an exception), or ``1`` if the interpreter exits due to an exception. If an + otherwise unhandled :exc:`SystemExit` is raised, the function will immediately + exit the process instead of returning ``1``. + + If :c:member:`PyConfig.inspect` is set (such as when the :option:`-i` option + is used), rather than returning when the interpreter exits, execution will + instead resume in an interactive Python prompt (REPL) using the ``__main__`` + module's global namespace. If the interpreter exited with an exception, it + is immediately raised in the REPL session. The function return value is + then determined by the way the *REPL session* terminates: returning ``0`` + if the session terminates without raising an unhandled exception, exiting + immediately for an unhandled :exc:`SystemExit`, and returning ``1`` for + any other unhandled exception. + + This function always finalizes the Python interpreter regardless of whether + it returns a value or immediately exits the process due to an unhandled + :exc:`SystemExit` exception. + + See :ref:`Python Configuration ` for an example of a + customized Python that always runs in isolated mode using + :c:func:`Py_RunMain`. + + Process-wide parameters ======================= diff --git a/Doc/c-api/init_config.rst b/Doc/c-api/init_config.rst index 9dc9ba6..6f8962a 100644 --- a/Doc/c-api/init_config.rst +++ b/Doc/c-api/init_config.rst @@ -1356,14 +1356,13 @@ the :option:`-X` command line option. The ``show_alloc_count`` field has been removed. +.. _init-from-config: + Initialization with PyConfig ---------------------------- -Function to initialize Python: - -.. c:function:: PyStatus Py_InitializeFromConfig(const PyConfig *config) - - Initialize Python from *config* configuration. +Initializing the interpreter from a populated configuration struct is handled +by calling :c:func:`Py_InitializeFromConfig`. The caller is responsible to handle exceptions (error or exit) using :c:func:`PyStatus_Exception` and :c:func:`Py_ExitStatusException`. @@ -1835,26 +1834,6 @@ return ``-1`` on error: } -Py_RunMain() -============ - -.. c:function:: int Py_RunMain(void) - - Execute the command (:c:member:`PyConfig.run_command`), the script - (:c:member:`PyConfig.run_filename`) or the module - (:c:member:`PyConfig.run_module`) specified on the command line or in the - configuration. - - By default and when if :option:`-i` option is used, run the REPL. - - Finally, finalizes Python and returns an exit status that can be passed to - the ``exit()`` function. - -See :ref:`Python Configuration ` for an example of -customized Python always running in isolated mode using -:c:func:`Py_RunMain`. - - Runtime Python configuration API ================================ diff --git a/Doc/c-api/veryhigh.rst b/Doc/c-api/veryhigh.rst index 6716744..9f02bdb 100644 --- a/Doc/c-api/veryhigh.rst +++ b/Doc/c-api/veryhigh.rst @@ -25,30 +25,6 @@ are only passed to these functions if it is certain that they were created by the same library that the Python runtime is using. -.. c:function:: int Py_Main(int argc, wchar_t **argv) - - The main program for the standard interpreter. This is made available for - programs which embed Python. The *argc* and *argv* parameters should be - prepared exactly as those which are passed to a C program's :c:func:`main` - function (converted to wchar_t according to the user's locale). It is - important to note that the argument list may be modified (but the contents of - the strings pointed to by the argument list are not). The return value will - be ``0`` if the interpreter exits normally (i.e., without an exception), - ``1`` if the interpreter exits due to an exception, or ``2`` if the parameter - list does not represent a valid Python command line. - - Note that if an otherwise unhandled :exc:`SystemExit` is raised, this - function will not return ``1``, but exit the process, as long as - :c:member:`PyConfig.inspect` is zero. - - -.. c:function:: int Py_BytesMain(int argc, char **argv) - - Similar to :c:func:`Py_Main` but *argv* is an array of bytes strings. - - .. versionadded:: 3.8 - - .. c:function:: int PyRun_AnyFile(FILE *fp, const char *filename) This is a simplified interface to :c:func:`PyRun_AnyFileExFlags` below, leaving diff --git a/Lib/test/test_embed.py b/Lib/test/test_embed.py index 3edc19d..035d441 100644 --- a/Lib/test/test_embed.py +++ b/Lib/test/test_embed.py @@ -168,7 +168,8 @@ class EmbeddingTestsMixin: # Parse the line from the loop. The first line is the main # interpreter and the 3 afterward are subinterpreters. interp = Interp(*match.groups()) - if support.verbose > 1: + if support.verbose > 2: + # 5 lines per pass is super-spammy, so limit that to -vvv print(interp) self.assertTrue(interp.interp) self.assertTrue(interp.tstate) @@ -279,6 +280,10 @@ class EmbeddingTests(EmbeddingTestsMixin, unittest.TestCase): """ env = dict(os.environ, PYTHONPATH=os.pathsep.join(sys.path)) out, err = self.run_embedded_interpreter("test_pre_initialization_api", env=env) + if support.verbose > 1: + print() + print(out) + print(err) if MS_WINDOWS: expected_path = self.test_exe else: @@ -296,6 +301,10 @@ class EmbeddingTests(EmbeddingTestsMixin, unittest.TestCase): env['PYTHONPATH'] = os.pathsep.join(sys.path) out, err = self.run_embedded_interpreter( "test_pre_initialization_sys_options", env=env) + if support.verbose > 1: + print() + print(out) + print(err) expected_output = ( "sys.warnoptions: ['once', 'module', 'default']\n" "sys._xoptions: {'not_an_option': '1', 'also_not_an_option': '2'}\n" diff --git a/Misc/NEWS.d/next/C API/2018-06-30-21-48-16.bpo-34008.2Wjtm0.rst b/Misc/NEWS.d/next/C API/2018-06-30-21-48-16.bpo-34008.2Wjtm0.rst new file mode 100644 index 0000000..1a01daf --- /dev/null +++ b/Misc/NEWS.d/next/C API/2018-06-30-21-48-16.bpo-34008.2Wjtm0.rst @@ -0,0 +1,2 @@ +Added ``Py_IsInitialized`` to the list of APIs that are safe to call before +the interpreter is initialized, and updated the embedding tests to cover it. diff --git a/Misc/NEWS.d/next/Documentation/2018-07-04-20-35-25.bpo-34008.bqecIb.rst b/Misc/NEWS.d/next/Documentation/2018-07-04-20-35-25.bpo-34008.bqecIb.rst new file mode 100644 index 0000000..a89086a --- /dev/null +++ b/Misc/NEWS.d/next/Documentation/2018-07-04-20-35-25.bpo-34008.bqecIb.rst @@ -0,0 +1,8 @@ +The :c:func:`Py_Main` documentation moved from the "Very High Level API" section to the +"Initialization and Finalization" section. + +Also make it explicit that we expect ``Py_Main`` to typically be called instead +of ``Py_Initialize`` rather than after it (since ``Py_Main`` makes its own +call to ``Py_Initialize``). Document that calling both is +supported but is version dependent on which settings +will be applied correctly. diff --git a/Programs/_testembed.c b/Programs/_testembed.c index ab2b2d0..ab619e3 100644 --- a/Programs/_testembed.c +++ b/Programs/_testembed.c @@ -311,14 +311,36 @@ static int test_pre_initialization_api(void) _Py_EMBED_PREINIT_CHECK("Checking Py_SetProgramName\n"); Py_SetProgramName(program); + _Py_EMBED_PREINIT_CHECK("Checking !Py_IsInitialized pre-initialization\n"); + if (Py_IsInitialized()) { + fprintf(stderr, "Fatal error: initialized before initialization!\n"); + return 1; + } + _Py_EMBED_PREINIT_CHECK("Initializing interpreter\n"); Py_Initialize(); + + _Py_EMBED_PREINIT_CHECK("Checking Py_IsInitialized post-initialization\n"); + if (!Py_IsInitialized()) { + fprintf(stderr, "Fatal error: not initialized after initialization!\n"); + return 1; + } + _Py_EMBED_PREINIT_CHECK("Check sys module contents\n"); - PyRun_SimpleString("import sys; " - "print('sys.executable:', sys.executable)"); + PyRun_SimpleString( + "import sys; " + "print('sys.executable:', sys.executable); " + "sys.stdout.flush(); " + ); _Py_EMBED_PREINIT_CHECK("Finalizing interpreter\n"); Py_Finalize(); + _Py_EMBED_PREINIT_CHECK("Checking !Py_IsInitialized post-finalization\n"); + if (Py_IsInitialized()) { + fprintf(stderr, "Fatal error: still initialized after finalization!\n"); + return 1; + } + _Py_EMBED_PREINIT_CHECK("Freeing memory allocated by Py_DecodeLocale\n"); PyMem_RawFree(program); return 0; @@ -364,12 +386,15 @@ static int test_pre_initialization_sys_options(void) _Py_EMBED_PREINIT_CHECK("Initializing interpreter\n"); _testembed_Py_InitializeFromConfig(); _Py_EMBED_PREINIT_CHECK("Check sys module contents\n"); - PyRun_SimpleString("import sys; " - "print('sys.warnoptions:', sys.warnoptions); " - "print('sys._xoptions:', sys._xoptions); " - "warnings = sys.modules['warnings']; " - "latest_filters = [f[0] for f in warnings.filters[:3]]; " - "print('warnings.filters[:3]:', latest_filters)"); + PyRun_SimpleString( + "import sys; " + "print('sys.warnoptions:', sys.warnoptions); " + "print('sys._xoptions:', sys._xoptions); " + "warnings = sys.modules['warnings']; " + "latest_filters = [f[0] for f in warnings.filters[:3]]; " + "print('warnings.filters[:3]:', latest_filters); " + "sys.stdout.flush(); " + ); _Py_EMBED_PREINIT_CHECK("Finalizing interpreter\n"); Py_Finalize(); -- cgit v0.12 a> 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 

/* Write Python objects to files and read them back.
   This is intended for writing and reading compiled Python code only;
   a true persistent storage facility would be much harder, since
   it would have to take circular links and sharing into account. */

#define PY_SSIZE_T_CLEAN

#include "Python.h"
#include "longintrepr.h"
#include "code.h"
#include "marshal.h"

#define ABS(x) ((x) < 0 ? -(x) : (x))

/* High water mark to determine when the marshalled object is dangerously deep
 * and risks coring the interpreter.  When the object stack gets this deep,
 * raise an exception instead of continuing.
 * On Windows debug builds, reduce this value.
 */
#if defined(MS_WINDOWS) && defined(_DEBUG)
#define MAX_MARSHAL_STACK_DEPTH 1500
#else
#define MAX_MARSHAL_STACK_DEPTH 2000
#endif

#define TYPE_NULL               '0'
#define TYPE_NONE               'N'
#define TYPE_FALSE              'F'
#define TYPE_TRUE               'T'
#define TYPE_STOPITER           'S'
#define TYPE_ELLIPSIS           '.'
#define TYPE_INT                'i'
/* TYPE_INT64 is deprecated. It is not
   generated anymore, and support for reading it
   will be removed in Python 3.4. */
#define TYPE_INT64              'I'
#define TYPE_FLOAT              'f'
#define TYPE_BINARY_FLOAT       'g'
#define TYPE_COMPLEX            'x'
#define TYPE_BINARY_COMPLEX     'y'
#define TYPE_LONG               'l'
#define TYPE_STRING             's'
#define TYPE_TUPLE              '('
#define TYPE_LIST               '['
#define TYPE_DICT               '{'
#define TYPE_CODE               'c'
#define TYPE_UNICODE            'u'
#define TYPE_UNKNOWN            '?'
#define TYPE_SET                '<'
#define TYPE_FROZENSET          '>'

#define WFERR_OK 0
#define WFERR_UNMARSHALLABLE 1
#define WFERR_NESTEDTOODEEP 2
#define WFERR_NOMEMORY 3

typedef struct {
    FILE *fp;
    int error;  /* see WFERR_* values */
    int depth;
    /* If fp == NULL, the following are valid: */
    PyObject *readable;    /* Stream-like object being read from */
    PyObject *str;
    PyObject *current_filename;
    char *ptr;
    char *end;
    int version;
} WFILE;

#define w_byte(c, p) if (((p)->fp)) putc((c), (p)->fp); \
                      else if ((p)->ptr != (p)->end) *(p)->ptr++ = (c); \
                           else w_more(c, p)

static void
w_more(int c, WFILE *p)
{
    Py_ssize_t size, newsize;
    if (p->str == NULL)
        return; /* An error already occurred */
    size = PyBytes_Size(p->str);
    newsize = size + size + 1024;
    if (newsize > 32*1024*1024) {
        newsize = size + (size >> 3);           /* 12.5% overallocation */
    }
    if (_PyBytes_Resize(&p->str, newsize) != 0) {
        p->ptr = p->end = NULL;
    }
    else {
        p->ptr = PyBytes_AS_STRING((PyBytesObject *)p->str) + size;
        p->end =
            PyBytes_AS_STRING((PyBytesObject *)p->str) + newsize;
        *p->ptr++ = Py_SAFE_DOWNCAST(c, int, char);
    }
}

static void
w_string(char *s, int n, WFILE *p)
{
    if (p->fp != NULL) {
        fwrite(s, 1, n, p->fp);
    }
    else {
        while (--n >= 0) {
            w_byte(*s, p);
            s++;
        }
    }
}

static void
w_short(int x, WFILE *p)
{
    w_byte((char)( x      & 0xff), p);
    w_byte((char)((x>> 8) & 0xff), p);
}

static void
w_long(long x, WFILE *p)
{
    w_byte((char)( x      & 0xff), p);
    w_byte((char)((x>> 8) & 0xff), p);
    w_byte((char)((x>>16) & 0xff), p);
    w_byte((char)((x>>24) & 0xff), p);
}

/* We assume that Python longs are stored internally in base some power of
   2**15; for the sake of portability we'll always read and write them in base
   exactly 2**15. */

#define PyLong_MARSHAL_SHIFT 15
#define PyLong_MARSHAL_BASE ((short)1 << PyLong_MARSHAL_SHIFT)
#define PyLong_MARSHAL_MASK (PyLong_MARSHAL_BASE - 1)
#if PyLong_SHIFT % PyLong_MARSHAL_SHIFT != 0
#error "PyLong_SHIFT must be a multiple of PyLong_MARSHAL_SHIFT"
#endif
#define PyLong_MARSHAL_RATIO (PyLong_SHIFT / PyLong_MARSHAL_SHIFT)

static void
w_PyLong(const PyLongObject *ob, WFILE *p)
{
    Py_ssize_t i, j, n, l;
    digit d;

    w_byte(TYPE_LONG, p);
    if (Py_SIZE(ob) == 0) {
        w_long((long)0, p);
        return;
    }

    /* set l to number of base PyLong_MARSHAL_BASE digits */
    n = ABS(Py_SIZE(ob));
    l = (n-1) * PyLong_MARSHAL_RATIO;
    d = ob->ob_digit[n-1];
    assert(d != 0); /* a PyLong is always normalized */
    do {
        d >>= PyLong_MARSHAL_SHIFT;
        l++;
    } while (d != 0);
    w_long((long)(Py_SIZE(ob) > 0 ? l : -l), p);

    for (i=0; i < n-1; i++) {
        d = ob->ob_digit[i];
        for (j=0; j < PyLong_MARSHAL_RATIO; j++) {
            w_short(d & PyLong_MARSHAL_MASK, p);
            d >>= PyLong_MARSHAL_SHIFT;
        }
        assert (d == 0);
    }
    d = ob->ob_digit[n-1];
    do {
        w_short(d & PyLong_MARSHAL_MASK, p);
        d >>= PyLong_MARSHAL_SHIFT;
    } while (d != 0);
}

static void
w_object(PyObject *v, WFILE *p)
{
    Py_ssize_t i, n;

    p->depth++;

    if (p->depth > MAX_MARSHAL_STACK_DEPTH) {
        p->error = WFERR_NESTEDTOODEEP;
    }
    else if (v == NULL) {
        w_byte(TYPE_NULL, p);
    }
    else if (v == Py_None) {
        w_byte(TYPE_NONE, p);
    }
    else if (v == PyExc_StopIteration) {
        w_byte(TYPE_STOPITER, p);
    }
    else if (v == Py_Ellipsis) {
        w_byte(TYPE_ELLIPSIS, p);
    }
    else if (v == Py_False) {
        w_byte(TYPE_FALSE, p);
    }
    else if (v == Py_True) {
        w_byte(TYPE_TRUE, p);
    }
    else if (PyLong_CheckExact(v)) {
        long x = PyLong_AsLong(v);
        if ((x == -1)  && PyErr_Occurred()) {
            PyLongObject *ob = (PyLongObject *)v;
            PyErr_Clear();
            w_PyLong(ob, p);
        }
        else {
#if SIZEOF_LONG > 4
            long y = Py_ARITHMETIC_RIGHT_SHIFT(long, x, 31);
            if (y && y != -1) {
                /* Too large for TYPE_INT */
                w_PyLong((PyLongObject*)v, p);
            }
            else
#endif
            {
                w_byte(TYPE_INT, p);
                w_long(x, p);
            }
        }
    }
    else if (PyFloat_CheckExact(v)) {
        if (p->version > 1) {
            unsigned char buf[8];
            if (_PyFloat_Pack8(PyFloat_AsDouble(v),
                               buf, 1) < 0) {
                p->error = WFERR_UNMARSHALLABLE;
                return;
            }
            w_byte(TYPE_BINARY_FLOAT, p);
            w_string((char*)buf, 8, p);
        }
        else {
            char *buf = PyOS_double_to_string(PyFloat_AS_DOUBLE(v),
                                              'g', 17, 0, NULL);
            if (!buf) {
                p->error = WFERR_NOMEMORY;
                return;
            }
            n = strlen(buf);
            w_byte(TYPE_FLOAT, p);
            w_byte((int)n, p);
            w_string(buf, (int)n, p);
            PyMem_Free(buf);
        }
    }
    else if (PyComplex_CheckExact(v)) {
        if (p->version > 1) {
            unsigned char buf[8];
            if (_PyFloat_Pack8(PyComplex_RealAsDouble(v),
                               buf, 1) < 0) {
                p->error = WFERR_UNMARSHALLABLE;
                return;
            }
            w_byte(TYPE_BINARY_COMPLEX, p);
            w_string((char*)buf, 8, p);
            if (_PyFloat_Pack8(PyComplex_ImagAsDouble(v),
                               buf, 1) < 0) {
                p->error = WFERR_UNMARSHALLABLE;
                return;
            }
            w_string((char*)buf, 8, p);
        }
        else {
            char *buf;
            w_byte(TYPE_COMPLEX, p);
            buf = PyOS_double_to_string(PyComplex_RealAsDouble(v),
                                        'g', 17, 0, NULL);
            if (!buf) {
                p->error = WFERR_NOMEMORY;
                return;
            }
            n = strlen(buf);
            w_byte((int)n, p);
            w_string(buf, (int)n, p);
            PyMem_Free(buf);
            buf = PyOS_double_to_string(PyComplex_ImagAsDouble(v),
                                        'g', 17, 0, NULL);
            if (!buf) {
                p->error = WFERR_NOMEMORY;
                return;
            }
            n = strlen(buf);
            w_byte((int)n, p);
            w_string(buf, (int)n, p);
            PyMem_Free(buf);
        }
    }
    else if (PyBytes_CheckExact(v)) {
        w_byte(TYPE_STRING, p);
        n = PyBytes_GET_SIZE(v);
        if (n > INT_MAX) {
            /* huge strings are not supported */
            p->depth--;
            p->error = WFERR_UNMARSHALLABLE;
            return;
        }
        w_long((long)n, p);
        w_string(PyBytes_AS_STRING(v), (int)n, p);
    }
    else if (PyUnicode_CheckExact(v)) {
        PyObject *utf8;
        utf8 = PyUnicode_AsEncodedString(v, "utf8", "surrogatepass");
        if (utf8 == NULL) {
            p->depth--;
            p->error = WFERR_UNMARSHALLABLE;
            return;
        }
        w_byte(TYPE_UNICODE, p);
        n = PyBytes_GET_SIZE(utf8);
        if (n > INT_MAX) {
            p->depth--;
            p->error = WFERR_UNMARSHALLABLE;
            return;
        }
        w_long((long)n, p);
        w_string(PyBytes_AS_STRING(utf8), (int)n, p);
        Py_DECREF(utf8);
    }
    else if (PyTuple_CheckExact(v)) {
        w_byte(TYPE_TUPLE, p);
        n = PyTuple_Size(v);
        w_long((long)n, p);
        for (i = 0; i < n; i++) {
            w_object(PyTuple_GET_ITEM(v, i), p);
        }
    }
    else if (PyList_CheckExact(v)) {
        w_byte(TYPE_LIST, p);
        n = PyList_GET_SIZE(v);
        w_long((long)n, p);
        for (i = 0; i < n; i++) {
            w_object(PyList_GET_ITEM(v, i), p);
        }
    }
    else if (PyDict_CheckExact(v)) {
        Py_ssize_t pos;
        PyObject *key, *value;
        w_byte(TYPE_DICT, p);
        /* This one is NULL object terminated! */
        pos = 0;
        while (PyDict_Next(v, &pos, &key, &value)) {
            w_object(key, p);
            w_object(value, p);
        }
        w_object((PyObject *)NULL, p);
    }
    else if (PyAnySet_CheckExact(v)) {
        PyObject *value, *it;

        if (PyObject_TypeCheck(v, &PySet_Type))
            w_byte(TYPE_SET, p);
        else
            w_byte(TYPE_FROZENSET, p);
        n = PyObject_Size(v);
        if (n == -1) {
            p->depth--;
            p->error = WFERR_UNMARSHALLABLE;
            return;
        }
        w_long((long)n, p);
        it = PyObject_GetIter(v);
        if (it == NULL) {
            p->depth--;
            p->error = WFERR_UNMARSHALLABLE;
            return;
        }
        while ((value = PyIter_Next(it)) != NULL) {
            w_object(value, p);
            Py_DECREF(value);
        }
        Py_DECREF(it);
        if (PyErr_Occurred()) {
            p->depth--;
            p->error = WFERR_UNMARSHALLABLE;
            return;
        }
    }
    else if (PyCode_Check(v)) {
        PyCodeObject *co = (PyCodeObject *)v;
        w_byte(TYPE_CODE, p);
        w_long(co->co_argcount, p);
        w_long(co->co_kwonlyargcount, p);
        w_long(co->co_nlocals, p);
        w_long(co->co_stacksize, p);
        w_long(co->co_flags, p);
        w_object(co->co_code, p);
        w_object(co->co_consts, p);
        w_object(co->co_names, p);
        w_object(co->co_varnames, p);
        w_object(co->co_freevars, p);
        w_object(co->co_cellvars, p);
        w_object(co->co_filename, p);
        w_object(co->co_name, p);
        w_long(co->co_firstlineno, p);
        w_object(co->co_lnotab, p);
    }
    else if (PyObject_CheckBuffer(v)) {
        /* Write unknown buffer-style objects as a string */
        char *s;
        Py_buffer view;
        if (PyObject_GetBuffer(v, &view, PyBUF_SIMPLE) != 0) {
            w_byte(TYPE_UNKNOWN, p);
            p->depth--;
            p->error = WFERR_UNMARSHALLABLE;
            return;
        }
        w_byte(TYPE_STRING, p);
        n = view.len;
        s = view.buf;
        if (n > INT_MAX) {
            p->depth--;
            p->error = WFERR_UNMARSHALLABLE;
            return;
        }
        w_long((long)n, p);
        w_string(s, (int)n, p);
        PyBuffer_Release(&view);
    }
    else {
        w_byte(TYPE_UNKNOWN, p);
        p->error = WFERR_UNMARSHALLABLE;
    }
    p->depth--;
}

/* version currently has no effect for writing longs. */
void
PyMarshal_WriteLongToFile(long x, FILE *fp, int version)
{
    WFILE wf;
    wf.fp = fp;
    wf.error = WFERR_OK;
    wf.depth = 0;
    wf.version = version;
    w_long(x, &wf);
}

void
PyMarshal_WriteObjectToFile(PyObject *x, FILE *fp, int version)
{
    WFILE wf;
    wf.fp = fp;
    wf.error = WFERR_OK;
    wf.depth = 0;
    wf.version = version;
    w_object(x, &wf);
}

typedef WFILE RFILE; /* Same struct with different invariants */

#define rs_byte(p) (((p)->ptr < (p)->end) ? (unsigned char)*(p)->ptr++ : EOF)

static int
r_string(char *s, int n, RFILE *p)
{
    char *ptr;
    int read, left;

    if (!p->readable) {
        if (p->fp != NULL)
            /* The result fits into int because it must be <=n. */
            read = (int) fread(s, 1, n, p->fp);
        else {
            left = (int)(p->end - p->ptr);
            read = (left < n) ? left : n;
            memcpy(s, p->ptr, read);
            p->ptr += read;
        }
    }
    else {
        _Py_IDENTIFIER(read);

        PyObject *data = _PyObject_CallMethodId(p->readable, &PyId_read, "i", n);
        read = 0;
        if (data != NULL) {
            if (!PyBytes_Check(data)) {
                PyErr_Format(PyExc_TypeError,
                             "f.read() returned not bytes but %.100s",
                             data->ob_type->tp_name);
            }
            else {
                read = PyBytes_GET_SIZE(data);
                if (read > 0) {
                    ptr = PyBytes_AS_STRING(data);
                    memcpy(s, ptr, read);
                }
            }
            Py_DECREF(data);
        }
    }
    if (!PyErr_Occurred() && (read < n)) {
        PyErr_SetString(PyExc_EOFError, "EOF read where not expected");
    }
    return read;
}


static int
r_byte(RFILE *p)
{
    int c = EOF;
    unsigned char ch;
    int n;

    if (!p->readable)
        c = p->fp ? getc(p->fp) : rs_byte(p);
    else {
        n = r_string((char *) &ch, 1, p);
        if (n > 0)
            c = ch;
    }
    return c;
}

static int
r_short(RFILE *p)
{
    register short x;
    unsigned char buffer[2];

    r_string((char *) buffer, 2, p);
    x = buffer[0];
    x |= buffer[1] << 8;
    /* Sign-extension, in case short greater than 16 bits */
    x |= -(x & 0x8000);
    return x;
}

static long
r_long(RFILE *p)
{
    register long x;
    unsigned char buffer[4];

    r_string((char *) buffer, 4, p);
    x = buffer[0];
    x |= (long)buffer[1] << 8;
    x |= (long)buffer[2] << 16;
    x |= (long)buffer[3] << 24;
#if SIZEOF_LONG > 4
    /* Sign extension for 64-bit machines */
    x |= -(x & 0x80000000L);
#endif
    return x;
}

/* r_long64 deals with the TYPE_INT64 code.  On a machine with
   sizeof(long) > 4, it returns a Python int object, else a Python long
   object.  Note that w_long64 writes out TYPE_INT if 32 bits is enough,
   so there's no inefficiency here in returning a PyLong on 32-bit boxes
   for everything written via TYPE_INT64 (i.e., if an int is written via
   TYPE_INT64, it *needs* more than 32 bits).
*/
static PyObject *
r_long64(RFILE *p)
{
    PyObject *result = NULL;
    long lo4 = r_long(p);
    long hi4 = r_long(p);

    if (!PyErr_Occurred()) {
#if SIZEOF_LONG > 4
        long x = (hi4 << 32) | (lo4 & 0xFFFFFFFFL);
        result = PyLong_FromLong(x);
#else
        unsigned char buf[8];
        int one = 1;
        int is_little_endian = (int)*(char*)&one;
        if (is_little_endian) {
            memcpy(buf, &lo4, 4);
            memcpy(buf+4, &hi4, 4);
        }
        else {
            memcpy(buf, &hi4, 4);
            memcpy(buf+4, &lo4, 4);
        }
        result = _PyLong_FromByteArray(buf, 8, is_little_endian, 1);
#endif
    }
    return result;
}

static PyObject *
r_PyLong(RFILE *p)
{
    PyLongObject *ob;
    int size, i, j, md, shorts_in_top_digit;
    long n;
    digit d;

    n = r_long(p);
    if (PyErr_Occurred())
        return NULL;
    if (n == 0)
        return (PyObject *)_PyLong_New(0);
    if (n < -INT_MAX || n > INT_MAX) {
        PyErr_SetString(PyExc_ValueError,
                       "bad marshal data (long size out of range)");
        return NULL;
    }

    size = 1 + (ABS(n) - 1) / PyLong_MARSHAL_RATIO;
    shorts_in_top_digit = 1 + (ABS(n) - 1) % PyLong_MARSHAL_RATIO;
    ob = _PyLong_New(size);
    if (ob == NULL)
        return NULL;
    Py_SIZE(ob) = n > 0 ? size : -size;

    for (i = 0; i < size-1; i++) {
        d = 0;
        for (j=0; j < PyLong_MARSHAL_RATIO; j++) {
            md = r_short(p);
            if (PyErr_Occurred())
                break;
            if (md < 0 || md > PyLong_MARSHAL_BASE)
                goto bad_digit;
            d += (digit)md << j*PyLong_MARSHAL_SHIFT;
        }
        ob->ob_digit[i] = d;
    }
    d = 0;
    for (j=0; j < shorts_in_top_digit; j++) {
        md = r_short(p);
        if (PyErr_Occurred())
            break;
        if (md < 0 || md > PyLong_MARSHAL_BASE)
            goto bad_digit;
        /* topmost marshal digit should be nonzero */
        if (md == 0 && j == shorts_in_top_digit - 1) {
            Py_DECREF(ob);
            PyErr_SetString(PyExc_ValueError,
                "bad marshal data (unnormalized long data)");
            return NULL;
        }
        d += (digit)md << j*PyLong_MARSHAL_SHIFT;
    }
    if (PyErr_Occurred()) {
        Py_DECREF(ob);
        return NULL;
    }
    /* top digit should be nonzero, else the resulting PyLong won't be
       normalized */
    ob->ob_digit[size-1] = d;
    return (PyObject *)ob;
  bad_digit:
    Py_DECREF(ob);
    PyErr_SetString(PyExc_ValueError,
                    "bad marshal data (digit out of range in long)");
    return NULL;
}


static PyObject *
r_object(RFILE *p)
{
    /* NULL is a valid return value, it does not necessarily means that
       an exception is set. */
    PyObject *v, *v2;
    long i, n;
    int type = r_byte(p);
    PyObject *retval;

    p->depth++;

    if (p->depth > MAX_MARSHAL_STACK_DEPTH) {
        p->depth--;
        PyErr_SetString(PyExc_ValueError, "recursion limit exceeded");
        return NULL;
    }

    switch (type) {

    case EOF:
        PyErr_SetString(PyExc_EOFError,
                        "EOF read where object expected");
        retval = NULL;
        break;

    case TYPE_NULL:
        retval = NULL;
        break;

    case TYPE_NONE:
        Py_INCREF(Py_None);
        retval = Py_None;
        break;

    case TYPE_STOPITER:
        Py_INCREF(PyExc_StopIteration);
        retval = PyExc_StopIteration;
        break;

    case TYPE_ELLIPSIS:
        Py_INCREF(Py_Ellipsis);
        retval = Py_Ellipsis;
        break;

    case TYPE_FALSE:
        Py_INCREF(Py_False);
        retval = Py_False;
        break;

    case TYPE_TRUE:
        Py_INCREF(Py_True);
        retval = Py_True;
        break;

    case TYPE_INT:
        n = r_long(p);
        retval = PyErr_Occurred() ? NULL : PyLong_FromLong(n);
        break;

    case TYPE_INT64:
        retval = r_long64(p);
        break;

    case TYPE_LONG:
        retval = r_PyLong(p);
        break;

    case TYPE_FLOAT:
        {
            char buf[256];
            double dx;
            retval = NULL;
            n = r_byte(p);
            if (n == EOF || r_string(buf, (int)n, p) != n) {
                PyErr_SetString(PyExc_EOFError,
                    "EOF read where object expected");
                break;
            }
            buf[n] = '\0';
            dx = PyOS_string_to_double(buf, NULL, NULL);
            if (dx == -1.0 && PyErr_Occurred())
                break;
            retval = PyFloat_FromDouble(dx);
            break;
        }

    case TYPE_BINARY_FLOAT:
        {
            unsigned char buf[8];
            double x;
            if (r_string((char*)buf, 8, p) != 8) {
                PyErr_SetString(PyExc_EOFError,
                    "EOF read where object expected");
                retval = NULL;
                break;
            }
            x = _PyFloat_Unpack8(buf, 1);
            if (x == -1.0 && PyErr_Occurred()) {
                retval = NULL;
                break;
            }
            retval = PyFloat_FromDouble(x);
            break;
        }

    case TYPE_COMPLEX:
        {
            char buf[256];
            Py_complex c;
            retval = NULL;
            n = r_byte(p);
            if (n == EOF || r_string(buf, (int)n, p) != n) {
                PyErr_SetString(PyExc_EOFError,
                    "EOF read where object expected");
                break;
            }
            buf[n] = '\0';
            c.real = PyOS_string_to_double(buf, NULL, NULL);
            if (c.real == -1.0 && PyErr_Occurred())
                break;
            n = r_byte(p);
            if (n == EOF || r_string(buf, (int)n, p) != n) {
                PyErr_SetString(PyExc_EOFError,
                    "EOF read where object expected");
                break;
            }
            buf[n] = '\0';
            c.imag = PyOS_string_to_double(buf, NULL, NULL);
            if (c.imag == -1.0 && PyErr_Occurred())
                break;
            retval = PyComplex_FromCComplex(c);
            break;
        }

    case TYPE_BINARY_COMPLEX:
        {
            unsigned char buf[8];
            Py_complex c;
            if (r_string((char*)buf, 8, p) != 8) {
                PyErr_SetString(PyExc_EOFError,
                    "EOF read where object expected");
                retval = NULL;
                break;
            }
            c.real = _PyFloat_Unpack8(buf, 1);
            if (c.real == -1.0 && PyErr_Occurred()) {
                retval = NULL;
                break;
            }
            if (r_string((char*)buf, 8, p) != 8) {
                PyErr_SetString(PyExc_EOFError,
                    "EOF read where object expected");
                retval = NULL;
                break;
            }
            c.imag = _PyFloat_Unpack8(buf, 1);
            if (c.imag == -1.0 && PyErr_Occurred()) {
                retval = NULL;
                break;
            }
            retval = PyComplex_FromCComplex(c);
            break;
        }

    case TYPE_STRING:
        n = r_long(p);
        if (PyErr_Occurred()) {
            retval = NULL;
            break;
        }
        if (n < 0 || n > INT_MAX) {
            PyErr_SetString(PyExc_ValueError, "bad marshal data (string size out of range)");
            retval = NULL;
            break;
        }
        v = PyBytes_FromStringAndSize((char *)NULL, n);
        if (v == NULL) {
            retval = NULL;
            break;
        }
        if (r_string(PyBytes_AS_STRING(v), (int)n, p) != n) {
            Py_DECREF(v);
            PyErr_SetString(PyExc_EOFError,
                            "EOF read where object expected");
            retval = NULL;
            break;
        }
        retval = v;
        break;

    case TYPE_UNICODE:
        {
        char *buffer;

        n = r_long(p);
        if (PyErr_Occurred()) {
            retval = NULL;
            break;
        }
        if (n < 0 || n > INT_MAX) {
            PyErr_SetString(PyExc_ValueError, "bad marshal data (unicode size out of range)");
            retval = NULL;
            break;
        }
        buffer = PyMem_NEW(char, n);
        if (buffer == NULL) {
            retval = PyErr_NoMemory();
            break;
        }
        if (r_string(buffer, (int)n, p) != n) {
            PyMem_DEL(buffer);
            PyErr_SetString(PyExc_EOFError,
                "EOF read where object expected");
            retval = NULL;
            break;
        }
        v = PyUnicode_DecodeUTF8(buffer, n, "surrogatepass");
        PyMem_DEL(buffer);
        retval = v;
        break;
        }

    case TYPE_TUPLE:
        n = r_long(p);
        if (PyErr_Occurred()) {
            retval = NULL;
            break;
        }
        if (n < 0 || n > INT_MAX) {
            PyErr_SetString(PyExc_ValueError, "bad marshal data (tuple size out of range)");
            retval = NULL;
            break;
        }
        v = PyTuple_New((int)n);
        if (v == NULL) {
            retval = NULL;
            break;
        }
        for (i = 0; i < n; i++) {
            v2 = r_object(p);
            if ( v2 == NULL ) {
                if (!PyErr_Occurred())
                    PyErr_SetString(PyExc_TypeError,
                        "NULL object in marshal data for tuple");
                Py_DECREF(v);
                v = NULL;
                break;
            }
            PyTuple_SET_ITEM(v, (int)i, v2);
        }
        retval = v;
        break;

    case TYPE_LIST:
        n = r_long(p);
        if (PyErr_Occurred()) {
            retval = NULL;
            break;
        }
        if (n < 0 || n > INT_MAX) {
            PyErr_SetString(PyExc_ValueError, "bad marshal data (list size out of range)");
            retval = NULL;
            break;
        }
        v = PyList_New((int)n);
        if (v == NULL) {
            retval = NULL;
            break;
        }
        for (i = 0; i < n; i++) {
            v2 = r_object(p);
            if ( v2 == NULL ) {
                if (!PyErr_Occurred())
                    PyErr_SetString(PyExc_TypeError,
                        "NULL object in marshal data for list");
                Py_DECREF(v);
                v = NULL;
                break;
            }
            PyList_SET_ITEM(v, (int)i, v2);
        }
        retval = v;
        break;

    case TYPE_DICT:
        v = PyDict_New();
        if (v == NULL) {
            retval = NULL;
            break;
        }
        for (;;) {
            PyObject *key, *val;
            key = r_object(p);
            if (key == NULL)
                break;
            val = r_object(p);
            if (val != NULL)
                PyDict_SetItem(v, key, val);
            Py_DECREF(key);
            Py_XDECREF(val);
        }
        if (PyErr_Occurred()) {
            Py_DECREF(v);
            v = NULL;
        }
        retval = v;
        break;

    case TYPE_SET:
    case TYPE_FROZENSET:
        n = r_long(p);
        if (PyErr_Occurred()) {
            retval = NULL;
            break;
        }
        if (n < 0 || n > INT_MAX) {
            PyErr_SetString(PyExc_ValueError, "bad marshal data (set size out of range)");
            retval = NULL;
            break;
        }
        v = (type == TYPE_SET) ? PySet_New(NULL) : PyFrozenSet_New(NULL);
        if (v == NULL) {
            retval = NULL;
            break;
        }
        for (i = 0; i < n; i++) {
            v2 = r_object(p);
            if ( v2 == NULL ) {
                if (!PyErr_Occurred())
                    PyErr_SetString(PyExc_TypeError,
                        "NULL object in marshal data for set");
                Py_DECREF(v);
                v = NULL;
                break;
            }
            if (PySet_Add(v, v2) == -1) {
                Py_DECREF(v);
                Py_DECREF(v2);
                v = NULL;
                break;
            }
            Py_DECREF(v2);
        }
        retval = v;
        break;

    case TYPE_CODE:
        {
            int argcount;
            int kwonlyargcount;
            int nlocals;
            int stacksize;
            int flags;
            PyObject *code = NULL;
            PyObject *consts = NULL;
            PyObject *names = NULL;
            PyObject *varnames = NULL;
            PyObject *freevars = NULL;
            PyObject *cellvars = NULL;
            PyObject *filename = NULL;
            PyObject *name = NULL;
            int firstlineno;
            PyObject *lnotab = NULL;

            v = NULL;

            /* XXX ignore long->int overflows for now */
            argcount = (int)r_long(p);
            if (PyErr_Occurred())
                goto code_error;
            kwonlyargcount = (int)r_long(p);
            if (PyErr_Occurred())
                goto code_error;
            nlocals = (int)r_long(p);
            if (PyErr_Occurred())
                goto code_error;
            stacksize = (int)r_long(p);
            if (PyErr_Occurred())
                goto code_error;
            flags = (int)r_long(p);
            if (PyErr_Occurred())
                goto code_error;
            code = r_object(p);
            if (code == NULL)
                goto code_error;
            consts = r_object(p);
            if (consts == NULL)
                goto code_error;
            names = r_object(p);
            if (names == NULL)
                goto code_error;
            varnames = r_object(p);
            if (varnames == NULL)
                goto code_error;
            freevars = r_object(p);
            if (freevars == NULL)
                goto code_error;
            cellvars = r_object(p);
            if (cellvars == NULL)
                goto code_error;
            filename = r_object(p);
            if (filename == NULL)
                goto code_error;
            if (PyUnicode_CheckExact(filename)) {
                if (p->current_filename != NULL) {
                    if (!PyUnicode_Compare(filename, p->current_filename)) {
                        Py_DECREF(filename);
                        Py_INCREF(p->current_filename);
                        filename = p->current_filename;
                    }
                }
                else {
                    p->current_filename = filename;
                }
            }
            name = r_object(p);
            if (name == NULL)
                goto code_error;
            firstlineno = (int)r_long(p);
            lnotab = r_object(p);
            if (lnotab == NULL)
                goto code_error;

            v = (PyObject *) PyCode_New(
                            argcount, kwonlyargcount,
                            nlocals, stacksize, flags,
                            code, consts, names, varnames,
                            freevars, cellvars, filename, name,
                            firstlineno, lnotab);

          code_error:
            Py_XDECREF(code);
            Py_XDECREF(consts);
            Py_XDECREF(names);
            Py_XDECREF(varnames);
            Py_XDECREF(freevars);
            Py_XDECREF(cellvars);
            Py_XDECREF(filename);
            Py_XDECREF(name);
            Py_XDECREF(lnotab);
        }
        retval = v;
        break;

    default:
        /* Bogus data got written, which isn't ideal.
           This will let you keep working and recover. */
        PyErr_SetString(PyExc_ValueError, "bad marshal data (unknown type code)");
        retval = NULL;
        break;

    }
    p->depth--;
    return retval;
}

static PyObject *
read_object(RFILE *p)
{
    PyObject *v;
    if (PyErr_Occurred()) {
        fprintf(stderr, "XXX readobject called with exception set\n");
        return NULL;
    }
    v = r_object(p);
    if (v == NULL && !PyErr_Occurred())
        PyErr_SetString(PyExc_TypeError, "NULL object in marshal data for object");
    return v;
}

int
PyMarshal_ReadShortFromFile(FILE *fp)
{
    RFILE rf;
    assert(fp);
    rf.readable = NULL;
    rf.fp = fp;
    rf.current_filename = NULL;
    rf.end = rf.ptr = NULL;
    return r_short(&rf);
}

long
PyMarshal_ReadLongFromFile(FILE *fp)
{
    RFILE rf;
    rf.fp = fp;
    rf.readable = NULL;
    rf.current_filename = NULL;
    rf.ptr = rf.end = NULL;
    return r_long(&rf);
}

#ifdef HAVE_FSTAT
/* Return size of file in bytes; < 0 if unknown. */
static off_t
getfilesize(FILE *fp)
{
    struct stat st;
    if (fstat(fileno(fp), &st) != 0)
        return -1;
    else
        return st.st_size;
}
#endif

/* If we can get the size of the file up-front, and it's reasonably small,
 * read it in one gulp and delegate to ...FromString() instead.  Much quicker
 * than reading a byte at a time from file; speeds .pyc imports.
 * CAUTION:  since this may read the entire remainder of the file, don't
 * call it unless you know you're done with the file.
 */
PyObject *
PyMarshal_ReadLastObjectFromFile(FILE *fp)
{
/* REASONABLE_FILE_LIMIT is by defn something big enough for Tkinter.pyc. */
#define REASONABLE_FILE_LIMIT (1L << 18)
#ifdef HAVE_FSTAT
    off_t filesize;
    filesize = getfilesize(fp);
    if (filesize > 0 && filesize <= REASONABLE_FILE_LIMIT) {
        char* pBuf = (char *)PyMem_MALLOC(filesize);
        if (pBuf != NULL) {
            PyObject* v;
            size_t n;
            /* filesize must fit into an int, because it
               is smaller than REASONABLE_FILE_LIMIT */
            n = fread(pBuf, 1, (int)filesize, fp);
            v = PyMarshal_ReadObjectFromString(pBuf, n);
            PyMem_FREE(pBuf);
            return v;
        }

    }
#endif
    /* We don't have fstat, or we do but the file is larger than
     * REASONABLE_FILE_LIMIT or malloc failed -- read a byte at a time.
     */
    return PyMarshal_ReadObjectFromFile(fp);

#undef REASONABLE_FILE_LIMIT
}

PyObject *
PyMarshal_ReadObjectFromFile(FILE *fp)
{
    RFILE rf;
    PyObject *result;
    rf.fp = fp;
    rf.readable = NULL;
    rf.current_filename = NULL;
    rf.depth = 0;
    rf.ptr = rf.end = NULL;
    result = r_object(&rf);
    return result;
}

PyObject *
PyMarshal_ReadObjectFromString(char *str, Py_ssize_t len)
{
    RFILE rf;
    PyObject *result;
    rf.fp = NULL;
    rf.readable = NULL;
    rf.current_filename = NULL;
    rf.ptr = str;
    rf.end = str + len;
    rf.depth = 0;
    result = r_object(&rf);
    return result;
}

PyObject *
PyMarshal_WriteObjectToString(PyObject *x, int version)
{
    WFILE wf;

    wf.fp = NULL;
    wf.readable = NULL;
    wf.str = PyBytes_FromStringAndSize((char *)NULL, 50);
    if (wf.str == NULL)
        return NULL;
    wf.ptr = PyBytes_AS_STRING((PyBytesObject *)wf.str);
    wf.end = wf.ptr + PyBytes_Size(wf.str);
    wf.error = WFERR_OK;
    wf.depth = 0;
    wf.version = version;
    w_object(x, &wf);
    if (wf.str != NULL) {
        char *base = PyBytes_AS_STRING((PyBytesObject *)wf.str);
        if (wf.ptr - base > PY_SSIZE_T_MAX) {
            Py_DECREF(wf.str);
            PyErr_SetString(PyExc_OverflowError,
                            "too much marshal data for a string");
            return NULL;
        }
        if (_PyBytes_Resize(&wf.str, (Py_ssize_t)(wf.ptr - base)) < 0)
            return NULL;
    }
    if (wf.error != WFERR_OK) {
        Py_XDECREF(wf.str);
        if (wf.error == WFERR_NOMEMORY)
            PyErr_NoMemory();
        else
            PyErr_SetString(PyExc_ValueError,
              (wf.error==WFERR_UNMARSHALLABLE)?"unmarshallable object"
               :"object too deeply nested to marshal");
        return NULL;
    }
    return wf.str;
}

/* And an interface for Python programs... */

static PyObject *
marshal_dump(PyObject *self, PyObject *args)
{
    /* XXX Quick hack -- need to do this differently */
    PyObject *x;
    PyObject *f;
    int version = Py_MARSHAL_VERSION;
    PyObject *s;
    PyObject *res;
    _Py_IDENTIFIER(write);

    if (!PyArg_ParseTuple(args, "OO|i:dump", &x, &f, &version))
        return NULL;
    s = PyMarshal_WriteObjectToString(x, version);
    if (s == NULL)
        return NULL;
    res = _PyObject_CallMethodId(f, &PyId_write, "O", s);
    Py_DECREF(s);
    return res;
}

PyDoc_STRVAR(dump_doc,
"dump(value, file[, version])\n\
\n\
Write the value on the open file. The value must be a supported type.\n\
The file must be an open file object such as sys.stdout or returned by\n\
open() or os.popen(). It must be opened in binary mode ('wb' or 'w+b').\n\
\n\
If the value has (or contains an object that has) an unsupported type, a\n\
ValueError exception is raised — but garbage data will also be written\n\
to the file. The object will not be properly read back by load()\n\
\n\
The version argument indicates the data format that dump should use.");

static PyObject *
marshal_load(PyObject *self, PyObject *f)
{
    PyObject *data, *result;
    _Py_IDENTIFIER(read);
    RFILE rf;

    /*
     * Make a call to the read method, but read zero bytes.
     * This is to ensure that the object passed in at least
     * has a read method which returns bytes.
     */
    data = _PyObject_CallMethodId(f, &PyId_read, "i", 0);
    if (data == NULL)
        return NULL;
    if (!PyBytes_Check(data)) {
        PyErr_Format(PyExc_TypeError,
                     "f.read() returned not bytes but %.100s",
                     data->ob_type->tp_name);
        result = NULL;
    }
    else {
        rf.depth = 0;
        rf.fp = NULL;
        rf.readable = f;
        rf.current_filename = NULL;
        result = read_object(&rf);
    }
    Py_DECREF(data);
    return result;
}

PyDoc_STRVAR(load_doc,
"load(file)\n\
\n\
Read one value from the open file and return it. If no valid value is\n\
read (e.g. because the data has a different Python version’s\n\
incompatible marshal format), raise EOFError, ValueError or TypeError.\n\
The file must be an open file object opened in binary mode ('rb' or\n\
'r+b').\n\
\n\
Note: If an object containing an unsupported type was marshalled with\n\
dump(), load() will substitute None for the unmarshallable type.");


static PyObject *
marshal_dumps(PyObject *self, PyObject *args)
{
    PyObject *x;
    int version = Py_MARSHAL_VERSION;
    if (!PyArg_ParseTuple(args, "O|i:dumps", &x, &version))
        return NULL;
    return PyMarshal_WriteObjectToString(x, version);
}

PyDoc_STRVAR(dumps_doc,
"dumps(value[, version])\n\
\n\
Return the string that would be written to a file by dump(value, file).\n\
The value must be a supported type. Raise a ValueError exception if\n\
value has (or contains an object that has) an unsupported type.\n\
\n\
The version argument indicates the data format that dumps should use.");


static PyObject *
marshal_loads(PyObject *self, PyObject *args)
{
    RFILE rf;
    Py_buffer p;
    char *s;
    Py_ssize_t n;
    PyObject* result;
    if (!PyArg_ParseTuple(args, "y*:loads", &p))
        return NULL;
    s = p.buf;
    n = p.len;
    rf.fp = NULL;
    rf.readable = NULL;
    rf.current_filename = NULL;
    rf.ptr = s;
    rf.end = s + n;
    rf.depth = 0;
    result = read_object(&rf);
    PyBuffer_Release(&p);
    return result;
}

PyDoc_STRVAR(loads_doc,
"loads(bytes)\n\
\n\
Convert the bytes object to a value. If no valid value is found, raise\n\
EOFError, ValueError or TypeError. Extra characters in the input are\n\
ignored.");

static PyMethodDef marshal_methods[] = {
    {"dump",            marshal_dump,   METH_VARARGS,   dump_doc},
    {"load",            marshal_load,   METH_O,         load_doc},
    {"dumps",           marshal_dumps,  METH_VARARGS,   dumps_doc},
    {"loads",           marshal_loads,  METH_VARARGS,   loads_doc},
    {NULL,              NULL}           /* sentinel */
};


PyDoc_STRVAR(module_doc,
"This module contains functions that can read and write Python values in\n\
a binary format. The format is specific to Python, but independent of\n\
machine architecture issues.\n\
\n\
Not all Python object types are supported; in general, only objects\n\
whose value is independent from a particular invocation of Python can be\n\
written and read by this module. The following types are supported:\n\
None, integers, floating point numbers, strings, bytes, bytearrays,\n\
tuples, lists, sets, dictionaries, and code objects, where it\n\
should be understood that tuples, lists and dictionaries are only\n\
supported as long as the values contained therein are themselves\n\
supported; and recursive lists and dictionaries should not be written\n\
(they will cause infinite loops).\n\
\n\
Variables:\n\
\n\
version -- indicates the format that the module uses. Version 0 is the\n\
    historical format, version 1 shares interned strings and version 2\n\
    uses a binary format for floating point numbers.\n\
\n\
Functions:\n\
\n\
dump() -- write value to a file\n\
load() -- read value from a file\n\
dumps() -- write value to a string\n\
loads() -- read value from a string");



static struct PyModuleDef marshalmodule = {
    PyModuleDef_HEAD_INIT,
    "marshal",
    module_doc,
    0,
    marshal_methods,
    NULL,
    NULL,
    NULL,
    NULL
};

PyMODINIT_FUNC
PyMarshal_Init(void)
{
    PyObject *mod = PyModule_Create(&marshalmodule);
    if (mod == NULL)
        return NULL;
    PyModule_AddIntConstant(mod, "version", Py_MARSHAL_VERSION);
    return mod;
}
generated by cgit v0.12 at 2025-07-09 03:42:26 (GMT)