GH-88116: Use a compact format to represent end line and column offsets. (GH-91666)

* Stores all location info in linetable to conform to PEP 626.

* Remove column table from code objects.

* Remove end-line table from code objects.

* Document new location table format

2 files changed, 54 insertions, 27 deletions

diff --git a/Include/cpython/code.h b/Include/cpython/code.h
index 6dc2290..be3b10b 100644
--- a/Include/cpython/code.h
+++ b/Include/cpython/code.h
@@ -86,15 +86,7 @@ typedef uint16_t _Py_CODEUNIT;
     PyObject *co_filename;        /* unicode (where it was loaded from) */     \
     PyObject *co_name;            /* unicode (name, for reference) */          \
     PyObject *co_qualname;        /* unicode (qualname, for reference) */      \
-    PyObject *co_linetable;       /* bytes (encoding addr<->lineno mapping)    \
-                                     See Objects/lnotab_notes.txt for details. \
-                                  */                                           \
-    PyObject *co_endlinetable;    /* bytes object that holds end lineno for    \
-                                     instructions separated across different   \
-                                     lines */                                  \
-    PyObject *co_columntable;     /* bytes object that holds start/end column  \
-                                     offset each instruction */                \
-                                                                               \
+    PyObject *co_linetable;       /* bytes object that holds location info */  \
     PyObject *co_weakreflist;     /* to support weakrefs to code objects */    \
     /* Scratch space for extra data relating to the code object.               \
        Type is a void* to keep the format private in codeobject.c to force     \
@@ -153,13 +145,13 @@ PyAPI_FUNC(PyCodeObject *) PyCode_New(
         int, int, int, int, int, PyObject *, PyObject *,
         PyObject *, PyObject *, PyObject *, PyObject *,
         PyObject *, PyObject *, PyObject *, int, PyObject *,
-        PyObject *, PyObject *, PyObject *);
+        PyObject *);
 
 PyAPI_FUNC(PyCodeObject *) PyCode_NewWithPosOnlyArgs(
         int, int, int, int, int, int, PyObject *, PyObject *,
         PyObject *, PyObject *, PyObject *, PyObject *,
         PyObject *, PyObject *, PyObject *, int, PyObject *,
-        PyObject *, PyObject *, PyObject *);
+        PyObject *);
         /* same as struct above */
 
 /* Creates a new empty code object with the specified source location. */
@@ -176,8 +168,8 @@ PyAPI_FUNC(int) PyCode_Addr2Location(PyCodeObject *, int, int *, int *, int *, i
 /* for internal use only */
 struct _opaque {
     int computed_line;
-    const char *lo_next;
-    const char *limit;
+    const uint8_t *lo_next;
+    const uint8_t *limit;
 };
 
 typedef struct _line_offsets {
@@ -210,6 +202,20 @@ PyAPI_FUNC(int) _PyCode_GetExtra(PyObject *code, Py_ssize_t index,
 PyAPI_FUNC(int) _PyCode_SetExtra(PyObject *code, Py_ssize_t index,
                                  void *extra);
 
+
+typedef enum _PyCodeLocationInfoKind {
+    /* short forms are 0 to 9 */
+    PY_CODE_LOCATION_INFO_SHORT0 = 0,
+    /* one lineforms are 10 to 12 */
+    PY_CODE_LOCATION_INFO_ONE_LINE0 = 10,
+    PY_CODE_LOCATION_INFO_ONE_LINE1 = 11,
+    PY_CODE_LOCATION_INFO_ONE_LINE2 = 12,
+
+    PY_CODE_LOCATION_INFO_NO_COLUMNS = 13,
+    PY_CODE_LOCATION_INFO_LONG = 14,
+    PY_CODE_LOCATION_INFO_NONE = 15
+} _PyCodeLocationInfoKind;
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/Include/internal/pycore_code.h b/Include/internal/pycore_code.h
index 8c868bc..3059db4 100644
--- a/Include/internal/pycore_code.h
+++ b/Include/internal/pycore_code.h
@@ -176,8 +176,6 @@ struct _PyCodeConstructor {
     PyObject *code;
     int firstlineno;
     PyObject *linetable;
-    PyObject *endlinetable;
-    PyObject *columntable;
 
     /* used by the code */
     PyObject *consts;
@@ -221,21 +219,10 @@ extern PyObject* _PyCode_GetCellvars(PyCodeObject *);
 extern PyObject* _PyCode_GetFreevars(PyCodeObject *);
 extern PyObject* _PyCode_GetCode(PyCodeObject *);
 
-/* Return the ending source code line number from a bytecode index. */
-extern int _PyCode_Addr2EndLine(PyCodeObject *, int);
-
-/* Return the ending source code line number from a bytecode index. */
-extern int _PyCode_Addr2EndLine(PyCodeObject *, int);
-/* Return the starting source code column offset from a bytecode index. */
-extern int _PyCode_Addr2Offset(PyCodeObject *, int);
-/* Return the ending source code column offset from a bytecode index. */
-extern int _PyCode_Addr2EndOffset(PyCodeObject *, int);
-
 /** API for initializing the line number tables. */
 extern int _PyCode_InitAddressRange(PyCodeObject* co, PyCodeAddressRange *bounds);
-extern int _PyCode_InitEndAddressRange(PyCodeObject* co, PyCodeAddressRange* bounds);
 
-/** Out of process API for initializing the line number table. */
+/** Out of process API for initializing the location table. */
 extern void _PyLineTable_InitAddressRange(
     const char *linetable,
     Py_ssize_t length,
@@ -445,6 +432,40 @@ read_obj(uint16_t *p)
     return (PyObject *)val;
 }
 
+static inline int
+write_varint(uint8_t *ptr, unsigned int val)
+{
+    int written = 1;
+    while (val >= 64) {
+        *ptr++ = 64 | (val & 63);
+        val >>= 6;
+        written++;
+    }
+    *ptr = val;
+    return written;
+}
+
+static inline int
+write_signed_varint(uint8_t *ptr, int val)
+{
+    if (val < 0) {
+        val = ((-val)<<1) | 1;
+    }
+    else {
+        val = val << 1;
+    }
+    return write_varint(ptr, val);
+}
+
+static inline int
+write_location_entry_start(uint8_t *ptr, int code, int length)
+{
+    assert((code & 15) == code);
+    *ptr = 128 | (code << 3) | (length - 1);
+    return 1;
+}
+
+
 #ifdef __cplusplus
 }
 #endif