SF patch #1035498: -m option to run a module as a script

(Contributed by Nick Coghlan.)

5 files changed, 109 insertions, 11 deletions

diff --git a/Doc/tut/tut.tex b/Doc/tut/tut.tex
index 9cb665a..ba0e3fd 100644
--- a/Doc/tut/tut.tex
+++ b/Doc/tut/tut.tex
@@ -205,6 +205,11 @@ executes the statement(s) in \var{command}, analogous to the shell's
 or other characters that are special to the shell, it is best to quote 
 \var{command} in its entirety with double quotes.
 
+Some Python modules are also useful as scripts.  These can be invoked using
+\samp{\program{python} \programopt{-m} \var{module} [arg] ...}, which
+executes the source file for \var{module} as if you had spelled out its
+full name on the command line.
+
 Note that there is a difference between \samp{python file} and
 \samp{python <file}.  In the latter case, input requests from the
 program, such as calls to \function{input()} and \function{raw_input()}, are
@@ -229,9 +234,11 @@ one; when no script and no arguments are given, \code{sys.argv[0]} is
 an empty string.  When the script name is given as \code{'-'} (meaning 
 standard input), \code{sys.argv[0]} is set to \code{'-'}.  When
 \programopt{-c} \var{command} is used, \code{sys.argv[0]} is set to
-\code{'-c'}.  Options found after \programopt{-c} \var{command} are
-not consumed by the Python interpreter's option processing but left in
-\code{sys.argv} for the command to handle.
+\code{'-c'}.  When \programopt{-m} \var{module} is used, \code{sys.argv[0]} 
+is set to the full name of the located module.  Options found after 
+\programopt{-c} \var{command} or \programopt{-m} \var{module} are not consumed 
+by the Python interpreter's option processing but left in \code{sys.argv} for 
+the command or module to handle.
 
 \subsection{Interactive Mode \label{interactive}}
 
diff --git a/Include/import.h b/Include/import.h
index c2c869e..9f1c2be 100644
--- a/Include/import.h
+++ b/Include/import.h
@@ -21,6 +21,10 @@ PyAPI_FUNC(PyObject *) PyImport_ReloadModule(PyObject *m);
 PyAPI_FUNC(void) PyImport_Cleanup(void);
 PyAPI_FUNC(int) PyImport_ImportFrozenModule(char *);
 
+PyAPI_FUNC(struct filedescr *) _PyImport_FindModule(
+	const char *, PyObject *, char *, size_t, FILE **, PyObject **);
+PyAPI_FUNC(int) _PyImport_IsScript(struct filedescr *);
+
 PyAPI_FUNC(PyObject *)_PyImport_FindExtension(char *, char *);
 PyAPI_FUNC(PyObject *)_PyImport_FixupExtension(char *, char *);
 
diff --git a/Misc/NEWS b/Misc/NEWS
index 81db100..9e5477e 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -12,6 +12,9 @@ What's New in Python 2.4 beta 1?
 Core and builtins
 -----------------
 
+- Added a command line option, -m module, which searches sys.path for the
+  module and then runs it.  (Contributed by Nick Coghlan.)
+
 - The bytecode optimizer now folds tuples of constants into a single
   constant.
 
@@ -29,7 +32,9 @@ Extension modules
 
 - ``collections.deque`` objects didn't play quite right with garbage
   collection, which could lead to a segfault in a release build, or
-  an assert failure in a debug build.
+  an assert failure in a debug build.  Also, added overflow checks,
+  better detection of mutation during iteration, and shielded deque
+  comparisons from unusual subclass overrides of the __iter__() method.
 
 Library
 -------
diff --git a/Modules/main.c b/Modules/main.c
index bc543a4..1005b94 100644
--- a/Modules/main.c
+++ b/Modules/main.c
@@ -3,6 +3,7 @@
 #include "Python.h"
 #include "osdefs.h"
 #include "compile.h" /* For CO_FUTURE_DIVISION */
+#include "import.h"
 
 #ifdef __VMS
 #include <unixlib.h>
@@ -33,7 +34,7 @@ static char **orig_argv;
 static int  orig_argc;
 
 /* command line options */
-#define BASE_OPTS "c:dEhiOQ:StuUvVW:xX"
+#define BASE_OPTS "c:dEhim:OQ:StuUvVW:xX"
 
 #ifndef RISCOS
 #define PROGRAM_OPTS BASE_OPTS
@@ -47,7 +48,7 @@ extern int Py_RISCOSWimpFlag;
 
 /* Short usage message (with %s for argv0) */
 static char *usage_line =
-"usage: %s [option] ... [-c cmd | file | -] [arg] ...\n";
+"usage: %s [option] ... [-c cmd | -m mod | file | -] [arg] ...\n";
 
 /* Long usage message, split into parts < 512 bytes */
 static char *usage_1 = "\
@@ -60,15 +61,16 @@ Options and arguments (and corresponding environment variables):\n\
          and force prompts, even if stdin does not appear to be a terminal\n\
 ";
 static char *usage_2 = "\
+-m mod : run library module as a script (terminates option list)\n\
 -O     : optimize generated bytecode (a tad; also PYTHONOPTIMIZE=x)\n\
 -OO    : remove doc-strings in addition to the -O optimizations\n\
 -Q arg : division options: -Qold (default), -Qwarn, -Qwarnall, -Qnew\n\
 -S     : don't imply 'import site' on initialization\n\
 -t     : issue warnings about inconsistent tab usage (-tt: issue errors)\n\
 -u     : unbuffered binary stdout and stderr (also PYTHONUNBUFFERED=x)\n\
-         see man page for details on internal buffering relating to '-u'\n\
 ";
 static char *usage_3 = "\
+         see man page for details on internal buffering relating to '-u'\n\
 -v     : verbose (trace import statements) (also PYTHONVERBOSE=x)\n\
 -V     : print the Python version number and exit\n\
 -W arg : warning control (arg is action:message:category:module:lineno)\n\
@@ -130,6 +132,28 @@ static void RunStartupFile(PyCompilerFlags *cf)
 	}
 }
 
+/* Get the path to a top-level module */
+static struct filedescr * FindModule(const char *module,
+				     FILE **fp, char **filename)
+{
+	struct filedescr *fdescr = NULL;
+	*fp = NULL;
+	*filename = malloc(MAXPATHLEN);
+
+	if (*filename == NULL)
+		return NULL;
+
+	/* Find the actual module source code */
+	fdescr = _PyImport_FindModule(module, NULL,
+					*filename, MAXPATHLEN, fp, NULL);
+
+	if (fdescr == NULL) {
+		free(*filename);
+		*filename = NULL;
+	}
+
+	return fdescr;
+}
 
 /* Main program */
 
@@ -140,6 +164,7 @@ Py_Main(int argc, char **argv)
 	int sts;
 	char *command = NULL;
 	char *filename = NULL;
+	char *module = NULL;
 	FILE *fp = stdin;
 	char *p;
 	int inspect = 0;
@@ -177,6 +202,18 @@ Py_Main(int argc, char **argv)
 			break;
 		}
 
+		if (c == 'm') {
+			/* -m is the last option; following arguments
+			   that look like options are left for the
+			   module to interpret. */
+			module = malloc(strlen(_PyOS_optarg) + 2);
+			if (module == NULL)
+				Py_FatalError(
+				   "not enough memory to copy -m argument");
+			strcpy(module, _PyOS_optarg);
+			break;
+		}
+
 		switch (c) {
 
 		case 'd':
@@ -289,7 +326,7 @@ Py_Main(int argc, char **argv)
 	    (p = Py_GETENV("PYTHONUNBUFFERED")) && *p != '\0')
 		unbuffered = 1;
 
-	if (command == NULL && _PyOS_optind < argc &&
+	if (command == NULL && module == NULL && _PyOS_optind < argc &&
 	    strcmp(argv[_PyOS_optind], "-") != 0)
 	{
 #ifdef __VMS
@@ -381,7 +418,7 @@ Py_Main(int argc, char **argv)
 	Py_Initialize();
 
 	if (Py_VerboseFlag ||
-	    (command == NULL && filename == NULL && stdin_is_interactive)) {
+	    (command == NULL && filename == NULL && module == NULL && stdin_is_interactive)) {
 		fprintf(stderr, "Python %s on %s\n",
 			Py_GetVersion(), Py_GetPlatform());
  		if (!Py_NoSiteFlag)
@@ -394,9 +431,34 @@ Py_Main(int argc, char **argv)
 		argv[_PyOS_optind] = "-c";
 	}
 
+	if (module != NULL) {
+		/* Backup _PyOS_optind and find the real file */
+                struct filedescr *fdescr = NULL;
+		_PyOS_optind--;
+		if ((fdescr = FindModule(module, &fp, &filename))) {
+			argv[_PyOS_optind] = filename;
+		} else {
+			fprintf(stderr, "%s: module %s not found\n",
+				argv[0], module);
+			return 2;
+		}
+		if (!fp) {
+			fprintf(stderr,
+				"%s: module %s has no associated file\n",
+				argv[0], module);
+			return 2;
+		}
+		if (!_PyImport_IsScript(fdescr)) {
+			fprintf(stderr,
+				"%s: module %s not usable as script\n  (%s)\n",
+				argv[0], module, filename);
+			return 2;
+		}
+	}
+
 	PySys_SetArgv(argc-_PyOS_optind, argv+_PyOS_optind);
 
-	if ((inspect || (command == NULL && filename == NULL)) &&
+	if ((inspect || (command == NULL && filename == NULL && module == NULL)) &&
 	    isatty(fileno(stdin))) {
 		PyObject *v;
 		v = PyImport_ImportModule("readline");
@@ -409,6 +471,10 @@ Py_Main(int argc, char **argv)
 	if (command) {
 		sts = PyRun_SimpleStringFlags(command, &cf) != 0;
 		free(command);
+	} else if (module) {
+		sts = PyRun_AnyFileExFlags(fp, filename, 1, &cf) != 0;
+		free(module);
+		free(filename);
 	}
 	else {
 		if (filename == NULL && stdin_is_interactive) {
@@ -431,7 +497,7 @@ Py_Main(int argc, char **argv)
 	}
 
 	if (inspect && stdin_is_interactive &&
-	    (filename != NULL || command != NULL))
+	    (filename != NULL || command != NULL || module != NULL))
 		/* XXX */
 		sts = PyRun_AnyFileFlags(stdin, "<stdin>", &cf) != 0;
 
diff --git a/Python/import.c b/Python/import.c
index 8f81d6e..75c6d3e 100644
--- a/Python/import.c
+++ b/Python/import.c
@@ -1334,6 +1334,22 @@ find_module(char *fullname, char *subname, PyObject *path, char *buf,
 	return fdp;
 }
 
+/* Helpers for main.c
+ *  Find the source file corresponding to a named module
+ */
+struct filedescr *
+_PyImport_FindModule(const char *name, PyObject *path, char *buf,
+	    size_t buflen, FILE **p_fp, PyObject **p_loader)
+{
+	return find_module((char *) name, (char *) name, path,
+			   buf, buflen, p_fp, p_loader);
+}
+
+PyAPI_FUNC(int) _PyImport_IsScript(struct filedescr * fd)
+{
+	return fd->type == PY_SOURCE || fd->type == PY_COMPILED;
+}
+
 /* case_ok(char* buf, int len, int namelen, char* name)
  * The arguments here are tricky, best shown by example:
  *    /a/b/c/d/e/f/g/h/i/j/k/some_long_module_name.py\0