add column offset to all syntax errors

6 files changed, 60 insertions, 40 deletions

diff --git a/Include/symtable.h b/Include/symtable.h
index d5ef96f..9b1b75b 100644
--- a/Include/symtable.h
+++ b/Include/symtable.h
@@ -46,7 +46,9 @@ typedef struct _symtable_entry {
     unsigned ste_returns_value : 1;  /* true if namespace uses return with
                                         an argument */
     int ste_lineno;          /* first line of block */
+    int ste_col_offset;      /* offset of first line of block */
     int ste_opt_lineno;      /* lineno of last exec or import * */
+    int ste_opt_col_offset;  /* offset of last exec or import * */
     int ste_tmpname;         /* counter for listcomp temp vars */
     struct symtable *ste_table;
 } PySTEntryObject;
diff --git a/Misc/NEWS b/Misc/NEWS
index 8cb3ea3..9ac3e0d 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -10,9 +10,8 @@ What's New in Python 3.2 Alpha 3?
 Core and Builtins
 -----------------
 
-- Issue #9901: Destroying the GIL in Py_Finalize() can fail if some other
-  threads are still running.  Instead, reinitialize the GIL on a second
-  call to Py_Initialize().
+- All SyntaxErrors now have a column offset and therefore a caret when the error
+  is printed.
 
 - Issue #9252: PyImport_Import no longer uses a fromlist hack to return the
   module that was imported, but instead gets the module from sys.modules.
@@ -59,10 +58,6 @@ Core and Builtins
 Library
 -------
 
-- Issue #9877: Expose sysconfig.get_makefile_filename()
-
-- logging: Added hasHandlers() method to Logger and LoggerAdapter.
-
 - Issue #1686: Fix string.Template when overriding the pattern attribute.
 
 - Issue #9854: SocketIO objects now observe the RawIOBase interface in
diff --git a/Python/ast.c b/Python/ast.c
index 9f6b7ea..38643f6 100644
--- a/Python/ast.c
+++ b/Python/ast.c
@@ -90,7 +90,7 @@ new_identifier(const char* n, PyArena *arena)
 static int
 ast_error(const node *n, const char *errstr)
 {
-    PyObject *u = Py_BuildValue("zi", errstr, LINENO(n));
+    PyObject *u = Py_BuildValue("zii", errstr, LINENO(n), n->n_col_offset);
     if (!u)
         return 0;
     PyErr_SetObject(PyExc_SyntaxError, u);
@@ -101,7 +101,7 @@ ast_error(const node *n, const char *errstr)
 static void
 ast_error_finish(const char *filename)
 {
-    PyObject *type, *value, *tback, *errstr, *loc, *tmp;
+    PyObject *type, *value, *tback, *errstr, *offset, *loc, *tmp;
     long lineno;
 
     assert(PyErr_Occurred());
@@ -118,6 +118,11 @@ ast_error_finish(const char *filename)
         Py_DECREF(errstr);
         return;
     }
+    offset = PyTuple_GetItem(value, 2);
+    if (!offset) {
+        Py_DECREF(errstr);
+        return;
+    }
     Py_DECREF(value);
 
     loc = PyErr_ProgramText(filename, lineno);
@@ -125,7 +130,7 @@ ast_error_finish(const char *filename)
         Py_INCREF(Py_None);
         loc = Py_None;
     }
-    tmp = Py_BuildValue("(zlOO)", filename, lineno, Py_None, loc);
+    tmp = Py_BuildValue("(zlOO)", filename, lineno, offset, loc);
     Py_DECREF(loc);
     if (!tmp) {
         Py_DECREF(errstr);
diff --git a/Python/compile.c b/Python/compile.c
index 5341e6b..d29e48c 100644
--- a/Python/compile.c
+++ b/Python/compile.c
@@ -123,6 +123,7 @@ struct compiler_unit {
 
     int u_firstlineno; /* the first lineno of the block */
     int u_lineno;          /* the lineno for the current stmt */
+    int u_col_offset;      /* the offset of the current stmt */
     int u_lineno_set;  /* boolean to indicate whether instr
                           has been generated with current lineno */
 };
@@ -486,6 +487,7 @@ compiler_enter_scope(struct compiler *c, identifier name, void *key,
     u->u_nfblocks = 0;
     u->u_firstlineno = lineno;
     u->u_lineno = 0;
+    u->u_col_offset = 0;
     u->u_lineno_set = 0;
     u->u_consts = PyDict_New();
     if (!u->u_consts) {
@@ -1965,6 +1967,7 @@ compiler_try_except(struct compiler *c, stmt_ty s)
             return compiler_error(c, "default 'except:' must be last");
         c->u->u_lineno_set = 0;
         c->u->u_lineno = handler->lineno;
+        c->u->u_col_offset = handler->col_offset;
         except = compiler_new_block(c);
         if (except == NULL)
             return 0;
@@ -2247,6 +2250,7 @@ compiler_visit_stmt(struct compiler *c, stmt_ty s)
 
     /* Always assign a lineno to the next instruction for a stmt. */
     c->u->u_lineno = s->lineno;
+    c->u->u_col_offset = s->col_offset;
     c->u->u_lineno_set = 0;
 
     switch (s->kind) {
@@ -3122,6 +3126,8 @@ compiler_visit_expr(struct compiler *c, expr_ty e)
         c->u->u_lineno = e->lineno;
         c->u->u_lineno_set = 0;
     }
+    /* Updating the column offset is always harmless. */
+    c->u->u_col_offset = e->col_offset;
     switch (e->kind) {
     case BoolOp_kind:
         return compiler_boolop(c, e);
@@ -3363,8 +3369,8 @@ compiler_error(struct compiler *c, const char *errstr)
         Py_INCREF(Py_None);
         loc = Py_None;
     }
-    u = Py_BuildValue("(ziOO)", c->c_filename, c->u->u_lineno,
-                      Py_None, loc);
+    u = Py_BuildValue("(ziiO)", c->c_filename, c->u->u_lineno,
+                      c->u->u_col_offset, loc);
     if (!u)
         goto exit;
     v = Py_BuildValue("(zO)", errstr, u);
diff --git a/Python/future.c b/Python/future.c
index 515dcd9..551edc6 100644
--- a/Python/future.c
+++ b/Python/future.c
@@ -44,12 +44,12 @@ future_check_features(PyFutureFeatures *ff, stmt_ty s, const char *filename)
         } else if (strcmp(feature, "braces") == 0) {
             PyErr_SetString(PyExc_SyntaxError,
                             "not a chance");
-            PyErr_SyntaxLocation(filename, s->lineno);
+            PyErr_SyntaxLocationEx(filename, s->lineno, s->col_offset);
             return 0;
         } else {
             PyErr_Format(PyExc_SyntaxError,
                          UNDEFINED_FUTURE_FEATURE, feature);
-            PyErr_SyntaxLocation(filename, s->lineno);
+            PyErr_SyntaxLocationEx(filename, s->lineno, s->col_offset);
             return 0;
         }
     }
@@ -98,8 +98,7 @@ future_parse(PyFutureFeatures *ff, mod_ty mod, const char *filename)
                 if (done) {
                     PyErr_SetString(PyExc_SyntaxError,
                                     ERR_LATE_FUTURE);
-                    PyErr_SyntaxLocation(filename,
-                                         s->lineno);
+                    PyErr_SyntaxLocationEx(filename, s->lineno, s->col_offset);
                     return 0;
                 }
                 if (!future_check_features(ff, s, filename))
diff --git a/Python/symtable.c b/Python/symtable.c
index 55c9f47..f75b9c9 100644
--- a/Python/symtable.c
+++ b/Python/symtable.c
@@ -25,7 +25,7 @@
 
 static PySTEntryObject *
 ste_new(struct symtable *st, identifier name, _Py_block_ty block,
-              void *key, int lineno)
+        void *key, int lineno, int col_offset)
 {
     PySTEntryObject *ste = NULL;
     PyObject *k;
@@ -65,7 +65,9 @@ ste_new(struct symtable *st, identifier name, _Py_block_ty block,
     ste->ste_varargs = 0;
     ste->ste_varkeywords = 0;
     ste->ste_opt_lineno = 0;
+    ste->ste_opt_col_offset = 0;
     ste->ste_lineno = lineno;
+    ste->ste_col_offset = col_offset;
 
     if (st->st_cur != NULL &&
         (st->st_cur->ste_nested ||
@@ -163,7 +165,8 @@ PyTypeObject PySTEntry_Type = {
 static int symtable_analyze(struct symtable *st);
 static int symtable_warn(struct symtable *st, char *msg, int lineno);
 static int symtable_enter_block(struct symtable *st, identifier name,
-                                _Py_block_ty block, void *ast, int lineno);
+                                _Py_block_ty block, void *ast, int lineno,
+                                int col_offset);
 static int symtable_exit_block(struct symtable *st, void *ast);
 static int symtable_visit_stmt(struct symtable *st, stmt_ty s);
 static int symtable_visit_expr(struct symtable *st, expr_ty s);
@@ -230,7 +233,7 @@ PySymtable_Build(mod_ty mod, const char *filename, PyFutureFeatures *future)
     st->st_future = future;
     /* Make the initial symbol information gathering pass */
     if (!GET_IDENTIFIER(top) ||
-        !symtable_enter_block(st, top, ModuleBlock, (void *)mod, 0)) {
+        !symtable_enter_block(st, top, ModuleBlock, (void *)mod, 0, 0)) {
         PySymtable_Free(st);
         return NULL;
     }
@@ -390,8 +393,8 @@ analyze_name(PySTEntryObject *ste, PyObject *scopes, PyObject *name, long flags,
             PyErr_Format(PyExc_SyntaxError,
                         "name '%U' is parameter and global",
                         name);
-            PyErr_SyntaxLocation(ste->ste_table->st_filename,
-                                 ste->ste_lineno);
+            PyErr_SyntaxLocationEx(ste->ste_table->st_filename,
+                                   ste->ste_lineno, ste->ste_col_offset);
 
             return 0;
         }
@@ -534,8 +537,8 @@ check_unoptimized(const PySTEntryObject* ste) {
         break;
     }
 
-    PyErr_SyntaxLocation(ste->ste_table->st_filename,
-                         ste->ste_opt_lineno);
+    PyErr_SyntaxLocationEx(ste->ste_table->st_filename, ste->ste_opt_lineno,
+                           ste->ste_opt_col_offset);
     return 0;
 }
 
@@ -873,8 +876,8 @@ symtable_warn(struct symtable *st, char *msg, int lineno)
                            lineno, NULL, NULL) < 0)     {
         if (PyErr_ExceptionMatches(PyExc_SyntaxWarning)) {
             PyErr_SetString(PyExc_SyntaxError, msg);
-            PyErr_SyntaxLocation(st->st_filename,
-                                 st->st_cur->ste_lineno);
+            PyErr_SyntaxLocationEx(st->st_filename, st->st_cur->ste_lineno,
+                                   st->st_cur->ste_col_offset);
         }
         return 0;
     }
@@ -907,7 +910,7 @@ symtable_exit_block(struct symtable *st, void *ast)
 
 static int
 symtable_enter_block(struct symtable *st, identifier name, _Py_block_ty block,
-                     void *ast, int lineno)
+                     void *ast, int lineno, int col_offset)
 {
     PySTEntryObject *prev = NULL;
 
@@ -918,7 +921,7 @@ symtable_enter_block(struct symtable *st, identifier name, _Py_block_ty block,
         }
         Py_DECREF(st->st_cur);
     }
-    st->st_cur = ste_new(st, name, block, ast, lineno);
+    st->st_cur = ste_new(st, name, block, ast, lineno, col_offset);
     if (st->st_cur == NULL)
         return 0;
     if (name == GET_IDENTIFIER(top))
@@ -963,8 +966,9 @@ symtable_add_def(struct symtable *st, PyObject *name, int flag)
         if ((flag & DEF_PARAM) && (val & DEF_PARAM)) {
             /* Is it better to use 'mangled' or 'name' here? */
             PyErr_Format(PyExc_SyntaxError, DUPLICATE_ARGUMENT, name);
-            PyErr_SyntaxLocation(st->st_filename,
-                               st->st_cur->ste_lineno);
+            PyErr_SyntaxLocationEx(st->st_filename,
+                                   st->st_cur->ste_lineno,
+                                   st->st_cur->ste_col_offset);
             goto error;
         }
         val |= flag;
@@ -1114,7 +1118,8 @@ symtable_visit_stmt(struct symtable *st, stmt_ty s)
         if (s->v.FunctionDef.decorator_list)
             VISIT_SEQ(st, expr, s->v.FunctionDef.decorator_list);
         if (!symtable_enter_block(st, s->v.FunctionDef.name,
-                                  FunctionBlock, (void *)s, s->lineno))
+                                  FunctionBlock, (void *)s, s->lineno,
+                                  s->col_offset))
             return 0;
         VISIT_IN_BLOCK(st, arguments, s->v.FunctionDef.args, s);
         VISIT_SEQ_IN_BLOCK(st, stmt, s->v.FunctionDef.body, s);
@@ -1134,7 +1139,7 @@ symtable_visit_stmt(struct symtable *st, stmt_ty s)
         if (s->v.ClassDef.decorator_list)
             VISIT_SEQ(st, expr, s->v.ClassDef.decorator_list);
         if (!symtable_enter_block(st, s->v.ClassDef.name, ClassBlock,
-                                  (void *)s, s->lineno))
+                                  (void *)s, s->lineno, s->col_offset))
             return 0;
         if (!GET_IDENTIFIER(__class__) ||
             !symtable_add_def(st, __class__, DEF_LOCAL) ||
@@ -1158,8 +1163,9 @@ symtable_visit_stmt(struct symtable *st, stmt_ty s)
             if (st->st_cur->ste_generator) {
                 PyErr_SetString(PyExc_SyntaxError,
                     RETURN_VAL_IN_GENERATOR);
-                PyErr_SyntaxLocation(st->st_filename,
-                             s->lineno);
+                PyErr_SyntaxLocationEx(st->st_filename,
+                                       s->lineno,
+                                       s->col_offset);
                 return 0;
             }
         }
@@ -1221,15 +1227,19 @@ symtable_visit_stmt(struct symtable *st, stmt_ty s)
         VISIT_SEQ(st, alias, s->v.Import.names);
         /* XXX Don't have the lineno available inside
            visit_alias */
-        if (st->st_cur->ste_unoptimized && !st->st_cur->ste_opt_lineno)
+        if (st->st_cur->ste_unoptimized && !st->st_cur->ste_opt_lineno) {
             st->st_cur->ste_opt_lineno = s->lineno;
+            st->st_cur->ste_opt_col_offset = s->col_offset;
+        }
         break;
     case ImportFrom_kind:
         VISIT_SEQ(st, alias, s->v.ImportFrom.names);
         /* XXX Don't have the lineno available inside
            visit_alias */
-        if (st->st_cur->ste_unoptimized && !st->st_cur->ste_opt_lineno)
+        if (st->st_cur->ste_unoptimized && !st->st_cur->ste_opt_lineno) {
             st->st_cur->ste_opt_lineno = s->lineno;
+            st->st_cur->ste_opt_col_offset = s->col_offset;
+        }
         break;
     case Global_kind: {
         int i;
@@ -1324,7 +1334,8 @@ symtable_visit_expr(struct symtable *st, expr_ty e)
         if (e->v.Lambda.args->defaults)
             VISIT_SEQ(st, expr, e->v.Lambda.args->defaults);
         if (!symtable_enter_block(st, lambda,
-                                  FunctionBlock, (void *)e, e->lineno))
+                                  FunctionBlock, (void *)e, e->lineno,
+                                  e->col_offset))
             return 0;
         VISIT_IN_BLOCK(st, arguments, e->v.Lambda.args, (void*)e);
         VISIT_IN_BLOCK(st, expr, e->v.Lambda.body, (void*)e);
@@ -1367,8 +1378,8 @@ symtable_visit_expr(struct symtable *st, expr_ty e)
         if (st->st_cur->ste_returns_value) {
             PyErr_SetString(PyExc_SyntaxError,
                 RETURN_VAL_IN_GENERATOR);
-            PyErr_SyntaxLocation(st->st_filename,
-                         e->lineno);
+            PyErr_SyntaxLocationEx(st->st_filename,
+                                   e->lineno, e->col_offset);
             return 0;
         }
         break;
@@ -1557,8 +1568,9 @@ symtable_visit_alias(struct symtable *st, alias_ty a)
     else {
         if (st->st_cur->ste_type != ModuleBlock) {
         int lineno = st->st_cur->ste_lineno;
+        int col_offset = st->st_cur->ste_col_offset;
         PyErr_SetString(PyExc_SyntaxError, IMPORT_STAR_WARNING);
-        PyErr_SyntaxLocation(st->st_filename, lineno);
+        PyErr_SyntaxLocationEx(st->st_filename, lineno, col_offset);
         Py_DECREF(store_name);
         return 0;
         }
@@ -1622,7 +1634,8 @@ symtable_handle_comprehension(struct symtable *st, expr_ty e,
     VISIT(st, expr, outermost->iter);
     /* Create comprehension scope for the rest */
     if (!scope_name ||
-        !symtable_enter_block(st, scope_name, FunctionBlock, (void *)e, e->lineno)) {
+        !symtable_enter_block(st, scope_name, FunctionBlock, (void *)e,
+                              e->lineno, e->col_offset)) {
         return 0;
     }
     st->st_cur->ste_generator = is_generator;