Python/traceback.c

/* Traceback implementation */

#include "Python.h"
#include "internal/pystate.h"

#include "code.h"
#include "frameobject.h"
#include "structmember.h"
#include "osdefs.h"
#ifdef HAVE_FCNTL_H
#include <fcntl.h>
#endif

#define OFF(x) offsetof(PyTracebackObject, x)

#define PUTS(fd, str) _Py_write_noraise(fd, str, (int)strlen(str))
#define MAX_STRING_LENGTH 500
#define MAX_FRAME_DEPTH 100
#define MAX_NTHREADS 100

/* Function from Parser/tokenizer.c */
extern char * PyTokenizer_FindEncodingFilename(int, PyObject *);

_Py_IDENTIFIER(TextIOWrapper);
_Py_IDENTIFIER(close);
_Py_IDENTIFIER(open);
_Py_IDENTIFIER(path);

static PyObject *
tb_dir(PyTracebackObject *self)
{
    return Py_BuildValue("[ssss]", "tb_frame", "tb_next",
                                   "tb_lasti", "tb_lineno");
}

static PyMethodDef tb_methods[] = {
   {"__dir__", (PyCFunction)tb_dir, METH_NOARGS},
   {NULL, NULL, 0, NULL},
};

static PyMemberDef tb_memberlist[] = {
    {"tb_next",         T_OBJECT,       OFF(tb_next),   READONLY},
    {"tb_frame",        T_OBJECT,       OFF(tb_frame),  READONLY},
    {"tb_lasti",        T_INT,          OFF(tb_lasti),  READONLY},
    {"tb_lineno",       T_INT,          OFF(tb_lineno), READONLY},
    {NULL}      /* Sentinel */
};

static void
tb_dealloc(PyTracebackObject *tb)
{
    PyObject_GC_UnTrack(tb);
    Py_TRASHCAN_SAFE_BEGIN(tb)
    Py_XDECREF(tb->tb_next);
    Py_XDECREF(tb->tb_frame);
    PyObject_GC_Del(tb);
    Py_TRASHCAN_SAFE_END(tb)
}

static int
tb_traverse(PyTracebackObject *tb, visitproc visit, void *arg)
{
    Py_VISIT(tb->tb_next);
    Py_VISIT(tb->tb_frame);
    return 0;
}

static void
tb_clear(PyTracebackObject *tb)
{
    Py_CLEAR(tb->tb_next);
    Py_CLEAR(tb->tb_frame);
}

PyTypeObject PyTraceBack_Type = {
    PyVarObject_HEAD_INIT(&PyType_Type, 0)
    "traceback",
    sizeof(PyTracebackObject),
    0,
    (destructor)tb_dealloc, /*tp_dealloc*/
    0,                  /*tp_print*/
    0,    /*tp_getattr*/
    0,                  /*tp_setattr*/
    0,                  /*tp_reserved*/
    0,                  /*tp_repr*/
    0,                  /*tp_as_number*/
    0,                  /*tp_as_sequence*/
    0,                  /*tp_as_mapping*/
    0,                  /* tp_hash */
    0,                  /* tp_call */
    0,                  /* tp_str */
    PyObject_GenericGetAttr,                    /* tp_getattro */
    0,                  /* tp_setattro */
    0,                                          /* tp_as_buffer */
    Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC,/* tp_flags */
    0,                                          /* tp_doc */
    (traverseproc)tb_traverse,                  /* tp_traverse */
    (inquiry)tb_clear,                          /* tp_clear */
    0,                                          /* tp_richcompare */
    0,                                          /* tp_weaklistoffset */
    0,                                          /* tp_iter */
    0,                                          /* tp_iternext */
    tb_methods,         /* tp_methods */
    tb_memberlist,      /* tp_members */
    0,                                          /* tp_getset */
    0,                                          /* tp_base */
    0,                                          /* tp_dict */
};

static PyTracebackObject *
newtracebackobject(PyTracebackObject *next, PyFrameObject *frame)
{
    PyTracebackObject *tb;
    if ((next != NULL && !PyTraceBack_Check(next)) ||
                    frame == NULL || !PyFrame_Check(frame)) {
        PyErr_BadInternalCall();
        return NULL;
    }
    tb = PyObject_GC_New(PyTracebackObject, &PyTraceBack_Type);
    if (tb != NULL) {
        Py_XINCREF(next);
        tb->tb_next = next;
        Py_XINCREF(frame);
        tb->tb_frame = frame;
        tb->tb_lasti = frame->f_lasti;
        tb->tb_lineno = PyFrame_GetLineNumber(frame);
        PyObject_GC_Track(tb);
    }
    return tb;
}

int
PyTraceBack_Here(PyFrameObject *frame)
{
    PyObject *exc, *val, *tb, *newtb;
    PyErr_Fetch(&exc, &val, &tb);
    newtb = (PyObject *)newtracebackobject((PyTracebackObject *)tb, frame);
    if (newtb == NULL) {
        _PyErr_ChainExceptions(exc, val, tb);
        return -1;
    }
    PyErr_Restore(exc, val, newtb);
    Py_XDECREF(tb);
    return 0;
}

/* Insert a frame into the traceback for (funcname, filename, lineno). */
void _PyTraceback_Add(const char *funcname, const char *filename, int lineno)
{
    PyObject *globals;
    PyCodeObject *code;
    PyFrameObject *frame;
    PyObject *exc, *val, *tb;

    /* Save and clear the current exception. Python functions must not be
       called with an exception set. Calling Python functions happens when
       the codec of the filesystem encoding is implemented in pure Python. */
    PyErr_Fetch(&exc, &val, &tb);

    globals = PyDict_New();
    if (!globals)
        goto error;
    code = PyCode_NewEmpty(filename, funcname, lineno);
    if (!code) {
        Py_DECREF(globals);
        goto error;
    }
    frame = PyFrame_New(PyThreadState_Get(), code, globals, NULL);
    Py_DECREF(globals);
    Py_DECREF(code);
    if (!frame)
        goto error;
    frame->f_lineno = lineno;

    PyErr_Restore(exc, val, tb);
    PyTraceBack_Here(frame);
    Py_DECREF(frame);
    return;

error:
    _PyErr_ChainExceptions(exc, val, tb);
}

static PyObject *
_Py_FindSourceFile(PyObject *filename, char* namebuf, size_t namelen, PyObject *io)
{
    Py_ssize_t i;
    PyObject *binary;
    PyObject *v;
    Py_ssize_t npath;
    size_t taillen;
    PyObject *syspath;
    PyObject *path;
    const char* tail;
    PyObject *filebytes;
    const char* filepath;
    Py_ssize_t len;
    PyObject* result;

    filebytes = PyUnicode_EncodeFSDefault(filename);
    if (filebytes == NULL) {
        PyErr_Clear();
        return NULL;
    }
    filepath = PyBytes_AS_STRING(filebytes);

    /* Search tail of filename in sys.path before giving up */
    tail = strrchr(filepath, SEP);
    if (tail == NULL)
        tail = filepath;
    else
        tail++;
    taillen = strlen(tail);

    syspath = _PySys_GetObjectId(&PyId_path);
    if (syspath == NULL || !PyList_Check(syspath))
        goto error;
    npath = PyList_Size(syspath);

    for (i = 0; i < npath; i++) {
        v = PyList_GetItem(syspath, i);
        if (v == NULL) {
            PyErr_Clear();
            break;
        }
        if (!PyUnicode_Check(v))
            continue;
        path = PyUnicode_EncodeFSDefault(v);
        if (path == NULL) {
            PyErr_Clear();
            continue;
        }
        len = PyBytes_GET_SIZE(path);
        if (len + 1 + (Py_ssize_t)taillen >= (Py_ssize_t)namelen - 1) {
            Py_DECREF(path);
            continue; /* Too long */
        }
        strcpy(namebuf, PyBytes_AS_STRING(path));
        Py_DECREF(path);
        if (strlen(namebuf) != (size_t)len)
            continue; /* v contains '\0' */
        if (len > 0 && namebuf[len-1] != SEP)
            namebuf[len++] = SEP;
        strcpy(namebuf+len, tail);

        binary = _PyObject_CallMethodId(io, &PyId_open, "ss", namebuf, "rb");
        if (binary != NULL) {
            result = binary;
            goto finally;
        }
        PyErr_Clear();
    }
    goto error;

error:
    result = NULL;
finally:
    Py_DECREF(filebytes);
    return result;
}

int
_Py_DisplaySourceLine(PyObject *f, PyObject *filename, int lineno, int indent)
{
    int err = 0;
    int fd;
    int i;
    char *found_encoding;
    char *encoding;
    PyObject *io;
    PyObject *binary;
    PyObject *fob = NULL;
    PyObject *lineobj = NULL;
    PyObject *res;
    char buf[MAXPATHLEN+1];
    int kind;
    void *data;

    /* open the file */
    if (filename == NULL)
        return 0;

    io = PyImport_ImportModuleNoBlock("io");
    if (io == NULL)
        return -1;
    binary = _PyObject_CallMethodId(io, &PyId_open, "Os", filename, "rb");

    if (binary == NULL) {
        PyErr_Clear();

        binary = _Py_FindSourceFile(filename, buf, sizeof(buf), io);
        if (binary == NULL) {
            Py_DECREF(io);
            return -1;
        }
    }

    /* use the right encoding to decode the file as unicode */
    fd = PyObject_AsFileDescriptor(binary);
    if (fd < 0) {
        Py_DECREF(io);
        Py_DECREF(binary);
        return 0;
    }
    found_encoding = PyTokenizer_FindEncodingFilename(fd, filename);
    if (found_encoding == NULL)
        PyErr_Clear();
    encoding = (found_encoding != NULL) ? found_encoding : "utf-8";
    /* Reset position */
    if (lseek(fd, 0, SEEK_SET) == (off_t)-1) {
        Py_DECREF(io);
        Py_DECREF(binary);
        PyMem_FREE(found_encoding);
        return 0;
    }
    fob = _PyObject_CallMethodId(io, &PyId_TextIOWrapper, "Os", binary, encoding);
    Py_DECREF(io);
    PyMem_FREE(found_encoding);

    if (fob == NULL) {
        PyErr_Clear();

        res = _PyObject_CallMethodId(binary, &PyId_close, NULL);
        Py_DECREF(binary);
        if (res)
            Py_DECREF(res);
        else
            PyErr_Clear();
        return 0;
    }
    Py_DECREF(binary);

    /* get the line number lineno */
    for (i = 0; i < lineno; i++) {
        Py_XDECREF(lineobj);
        lineobj = PyFile_GetLine(fob, -1);
        if (!lineobj) {
            PyErr_Clear();
            err = -1;
            break;
        }
    }
    res = _PyObject_CallMethodId(fob, &PyId_close, NULL);
    if (res)
        Py_DECREF(res);
    else
        PyErr_Clear();
    Py_DECREF(fob);
    if (!lineobj || !PyUnicode_Check(lineobj)) {
        Py_XDECREF(lineobj);
        return err;
    }

    /* remove the indentation of the line */
    kind = PyUnicode_KIND(lineobj);
    data = PyUnicode_DATA(lineobj);
    for (i=0; i < PyUnicode_GET_LENGTH(lineobj); i++) {
        Py_UCS4 ch = PyUnicode_READ(kind, data, i);
        if (ch != ' ' && ch != '\t' && ch != '\014')
            break;
    }
    if (i) {
        PyObject *truncated;
        truncated = PyUnicode_Substring(lineobj, i, PyUnicode_GET_LENGTH(lineobj));
        if (truncated) {
            Py_DECREF(lineobj);
            lineobj = truncated;
        } else {
            PyErr_Clear();
        }
    }

    /* Write some spaces before the line */
    strcpy(buf, "          ");
    assert (strlen(buf) == 10);
    while (indent > 0) {
        if (indent < 10)
            buf[indent] = '\0';
        err = PyFile_WriteString(buf, f);
        if (err != 0)
            break;
        indent -= 10;
    }

    /* finally display the line */
    if (err == 0)
        err = PyFile_WriteObject(lineobj, f, Py_PRINT_RAW);
    Py_DECREF(lineobj);
    if  (err == 0)
        err = PyFile_WriteString("\n", f);
    return err;
}

static int
tb_displayline(PyObject *f, PyObject *filename, int lineno, PyObject *name)
{
    int err;
    PyObject *line;

    if (filename == NULL || name == NULL)
        return -1;
    line = PyUnicode_FromFormat("  File \"%U\", line %d, in %U\n",
                                filename, lineno, name);
    if (line == NULL)
        return -1;
    err = PyFile_WriteObject(line, f, Py_PRINT_RAW);
    Py_DECREF(line);
    if (err != 0)
        return err;
    /* ignore errors since we can't report them, can we? */
    if (_Py_DisplaySourceLine(f, filename, lineno, 4))
        PyErr_Clear();
    return err;
}

static int
tb_printinternal(PyTracebackObject *tb, PyObject *f, long limit)
{
    int err = 0;
    long depth = 0;
    PyObject *last_file = NULL;
    int last_line = -1;
    PyObject *last_name = NULL;
    long cnt = 0;
    PyObject *line;
    PyTracebackObject *tb1 = tb;
    while (tb1 != NULL) {
        depth++;
        tb1 = tb1->tb_next;
    }
    while (tb != NULL && err == 0) {
        if (depth <= limit) {
            if (last_file != NULL &&
                tb->tb_frame->f_code->co_filename == last_file &&
                last_line != -1 && tb->tb_lineno == last_line &&
                last_name != NULL &&
                tb->tb_frame->f_code->co_name == last_name) {
                    cnt++;
                } else {
                    if (cnt > 3) {
                        line = PyUnicode_FromFormat(
                        "  [Previous line repeated %d more times]\n", cnt-3);
                        err = PyFile_WriteObject(line, f, Py_PRINT_RAW);
                        Py_DECREF(line);
                    }
                    last_file = tb->tb_frame->f_code->co_filename;
                    last_line = tb->tb_lineno;
                    last_name = tb->tb_frame->f_code->co_name;
                    cnt = 0;
                }
            if (cnt < 3)
                err = tb_displayline(f,
                                     tb->tb_frame->f_code->co_filename,
                                     tb->tb_lineno,
                                     tb->tb_frame->f_code->co_name);
        }
        depth--;
        tb = tb->tb_next;
        if (err == 0)
            err = PyErr_CheckSignals();
    }
    if (cnt > 3) {
        line = PyUnicode_FromFormat(
        "  [Previous line repeated %d more times]\n", cnt-3);
        err = PyFile_WriteObject(line, f, Py_PRINT_RAW);
        Py_DECREF(line);
    }
    return err;
}

#define PyTraceBack_LIMIT 1000

int
PyTraceBack_Print(PyObject *v, PyObject *f)
{
    int err;
    PyObject *limitv;
    long limit = PyTraceBack_LIMIT;

    if (v == NULL)
        return 0;
    if (!PyTraceBack_Check(v)) {
        PyErr_BadInternalCall();
        return -1;
    }
    limitv = PySys_GetObject("tracebacklimit");
    if (limitv) {
        PyObject *exc_type, *exc_value, *exc_tb;

        PyErr_Fetch(&exc_type, &exc_value, &exc_tb);
        limit = PyLong_AsLong(limitv);
        if (limit == -1 && PyErr_Occurred()) {
            if (PyErr_ExceptionMatches(PyExc_OverflowError)) {
                limit = PyTraceBack_LIMIT;
            }
            else {
                Py_XDECREF(exc_type);
                Py_XDECREF(exc_value);
                Py_XDECREF(exc_tb);
                return 0;
            }
        }
        else if (limit <= 0) {
            limit = PyTraceBack_LIMIT;
        }
        PyErr_Restore(exc_type, exc_value, exc_tb);
    }
    err = PyFile_WriteString("Traceback (most recent call last):\n", f);
    if (!err)
        err = tb_printinternal((PyTracebackObject *)v, f, limit);
    return err;
}

/* Reverse a string. For example, "abcd" becomes "dcba".

   This function is signal safe. */

void
_Py_DumpDecimal(int fd, unsigned long value)
{
    /* maximum number of characters required for output of %lld or %p.
       We need at most ceil(log10(256)*SIZEOF_LONG_LONG) digits,
       plus 1 for the null byte.  53/22 is an upper bound for log10(256). */
    char buffer[1 + (sizeof(unsigned long)*53-1) / 22 + 1];
    char *ptr, *end;

    end = &buffer[Py_ARRAY_LENGTH(buffer) - 1];
    ptr = end;
    *ptr = '\0';
    do {
        --ptr;
        assert(ptr >= buffer);
        *ptr = '0' + (value % 10);
        value /= 10;
    } while (value);

    _Py_write_noraise(fd, ptr, end - ptr);
}

/* Format an integer in range [0; 0xffffffff] to hexadecimal of 'width' digits,
   and write it into the file fd.

   This function is signal safe. */

void
_Py_DumpHexadecimal(int fd, unsigned long value, Py_ssize_t width)
{
    char buffer[sizeof(unsigned long) * 2 + 1], *ptr, *end;
    const Py_ssize_t size = Py_ARRAY_LENGTH(buffer) - 1;

    if (width > size)
        width = size;
    /* it's ok if width is negative */

    end = &buffer[size];
    ptr = end;
    *ptr = '\0';
    do {
        --ptr;
        assert(ptr >= buffer);
        *ptr = Py_hexdigits[value & 15];
        value >>= 4;
    } while ((end - ptr) < width || value);

    _Py_write_noraise(fd, ptr, end - ptr);
}

void
_Py_DumpASCII(int fd, PyObject *text)
{
    PyASCIIObject *ascii = (PyASCIIObject *)text;
    Py_ssize_t i, size;
    int truncated;
    int kind;
    void *data = NULL;
    wchar_t *wstr = NULL;
    Py_UCS4 ch;

    if (!PyUnicode_Check(text))
        return;

    size = ascii->length;
    kind = ascii->state.kind;
    if (kind == PyUnicode_WCHAR_KIND) {
        wstr = ((PyASCIIObject *)text)->wstr;
        if (wstr == NULL)
            return;
        size = ((PyCompactUnicodeObject *)text)->wstr_length;
    }
    else if (ascii->state.compact) {
        if (ascii->state.ascii)
            data = ((PyASCIIObject*)text) + 1;
        else
            data = ((PyCompactUnicodeObject*)text) + 1;
    }
    else {
        data = ((PyUnicodeObject *)text)->data.any;
        if (data == NULL)
            return;
    }

    if (MAX_STRING_LENGTH < size) {
        size = MAX_STRING_LENGTH;
        truncated = 1;
    }
    else {
        truncated = 0;
    }

    for (i=0; i < size; i++) {
        if (kind != PyUnicode_WCHAR_KIND)
            ch = PyUnicode_READ(kind, data, i);
        else
            ch = wstr[i];
        if (' ' <= ch && ch <= 126) {
            /* printable ASCII character */
            char c = (char)ch;
            _Py_write_noraise(fd, &c, 1);
        }
        else if (ch <= 0xff) {
            PUTS(fd, "\\x");
            _Py_DumpHexadecimal(fd, ch, 2);
        }
        else if (ch <= 0xffff) {
            PUTS(fd, "\\u");
            _Py_DumpHexadecimal(fd, ch, 4);
        }
        else {
            PUTS(fd, "\\U");
            _Py_DumpHexadecimal(fd, ch, 8);
        }
    }
    if (truncated) {
        PUTS(fd, "...");
    }
}

/* Write a frame into the file fd: "File "xxx", line xxx in xxx".

   This function is signal safe. */

static void
dump_frame(int fd, PyFrameObject *frame)
{
    PyCodeObject *code;
    int lineno;

    code = frame->f_code;
    PUTS(fd, "  File ");
    if (code != NULL && code->co_filename != NULL
        && PyUnicode_Check(code->co_filename))
    {
        PUTS(fd, "\"");
        _Py_DumpASCII(fd, code->co_filename);
        PUTS(fd, "\"");
    } else {
        PUTS(fd, "???");
    }

    /* PyFrame_GetLineNumber() was introduced in Python 2.7.0 and 3.2.0 */
    lineno = PyCode_Addr2Line(code, frame->f_lasti);
    PUTS(fd, ", line ");
    if (lineno >= 0) {
        _Py_DumpDecimal(fd, (unsigned long)lineno);
    }
    else {
        PUTS(fd, "???");
    }
    PUTS(fd, " in ");

    if (code != NULL && code->co_name != NULL
       && PyUnicode_Check(code->co_name)) {
        _Py_DumpASCII(fd, code->co_name);
    }
    else {
        PUTS(fd, "???");
    }

    PUTS(fd, "\n");
}

static void
dump_traceback(int fd, PyThreadState *tstate, int write_header)
{
    PyFrameObject *frame;
    unsigned int depth;

    if (write_header)
        PUTS(fd, "Stack (most recent call first):\n");

    frame = _PyThreadState_GetFrame(tstate);
    if (frame == NULL)
        return;

    depth = 0;
    while (frame != NULL) {
        if (MAX_FRAME_DEPTH <= depth) {
            PUTS(fd, "  ...\n");
            break;
        }
        if (!PyFrame_Check(frame))
            break;
        dump_frame(fd, frame);
        frame = frame->f_back;
        depth++;
    }
}

/* Dump the traceback of a Python thread into fd. Use write() to write the
   traceback and retry if write() is interrupted by a signal (failed with
   EINTR), but don't call the Python signal handler.

   The caller is responsible to call PyErr_CheckSignals() to call Python signal
   handlers if signals were received. */
void
_Py_DumpTraceback(int fd, PyThreadState *tstate)
{
    dump_traceback(fd, tstate, 1);
}

/* Write the thread identifier into the file 'fd': "Current thread 0xHHHH:\" if
   is_current is true, "Thread 0xHHHH:\n" otherwise.

   This function is signal safe. */

static void
write_thread_id(int fd, PyThreadState *tstate, int is_current)
{
    if (is_current)
        PUTS(fd, "Current thread 0x");
    else
        PUTS(fd, "Thread 0x");
    _Py_DumpHexadecimal(fd,
                        tstate->thread_id,
                        sizeof(unsigned long) * 2);
    PUTS(fd, " (most recent call first):\n");
}

/* Dump the traceback of all Python threads into fd. Use write() to write the
   traceback and retry if write() is interrupted by a signal (failed with
   EINTR), but don't call the Python signal handler.

   The caller is responsible to call PyErr_CheckSignals() to call Python signal
   handlers if signals were received. */
const char*
_Py_DumpTracebackThreads(int fd, PyInterpreterState *interp,
                         PyThreadState *current_tstate)
{
    PyThreadState *tstate;
    unsigned int nthreads;

    if (current_tstate == NULL) {
        /* _Py_DumpTracebackThreads() is called from signal handlers by
           faulthandler.

           SIGSEGV, SIGFPE, SIGABRT, SIGBUS and SIGILL are synchronous signals
           and are thus delivered to the thread that caused the fault. Get the
           Python thread state of the current thread.

           PyThreadState_Get() doesn't give the state of the thread that caused
           the fault if the thread released the GIL, and so this function
           cannot be used. Read the thread specific storage (TSS) instead: call
           PyGILState_GetThisThreadState(). */
        current_tstate = PyGILState_GetThisThreadState();
    }

    if (interp == NULL) {
        if (current_tstate == NULL) {
            interp = _PyGILState_GetInterpreterStateUnsafe();
            if (interp == NULL) {
                /* We need the interpreter state to get Python threads */
                return "unable to get the interpreter state";
            }
        }
        else {
            interp = current_tstate->interp;
        }
    }
    assert(interp != NULL);

    /* Get the current interpreter from the current thread */
    tstate = PyInterpreterState_ThreadHead(interp);
    if (tstate == NULL)
        return "unable to get the thread head state";

    /* Dump the traceback of each thread */
    tstate = PyInterpreterState_ThreadHead(interp);
    nthreads = 0;
    _Py_BEGIN_SUPPRESS_IPH
    do
    {
        if (nthreads != 0)
            PUTS(fd, "\n");
        if (nthreads >= MAX_NTHREADS) {
            PUTS(fd, "...\n");
            break;
        }
        write_thread_id(fd, tstate, tstate == current_tstate);
        dump_traceback(fd, tstate, 0);
        tstate = PyThreadState_Next(tstate);
        nthreads++;
    } while (tstate != NULL);
    _Py_END_SUPPRESS_IPH

    return NULL;
}