py/lexer: Simplify lexer startup by using dummy bytes and next_char().

Now consistently uses the EOL processing ("\r" and "\r\n" convert to "\n")
and EOF processing (ensure "\n" before EOF) provided by next_char().

In particular the lexer can now correctly handle input that starts with CR.

1 files changed, 7 insertions, 22 deletions

diff --git a/py/lexer.c b/py/lexer.c
index 05651abec..4cbf31d90 100644
--- a/py/lexer.c
+++ b/py/lexer.c
@@ -677,7 +677,7 @@ mp_lexer_t *mp_lexer_new(qstr src_name, mp_reader_t reader) {
     lex->source_name = src_name;
     lex->reader = reader;
     lex->line = 1;
-    lex->column = 1;
+    lex->column = -2;   // account for 3 dummy bytes
     lex->emit_dent = 0;
     lex->nested_bracket_level = 0;
     lex->alloc_indent_level = MICROPY_ALLOC_LEXER_INDENT_INIT;
@@ -688,27 +688,12 @@ mp_lexer_t *mp_lexer_new(qstr src_name, mp_reader_t reader) {
     // store sentinel for first indentation level
     lex->indent_level[0] = 0;
 
-    // preload characters
-    lex->chr0 = reader.readbyte(reader.data);
-    lex->chr1 = reader.readbyte(reader.data);
-    lex->chr2 = reader.readbyte(reader.data);
-
-    // if input stream is 0, 1 or 2 characters long and doesn't end in a newline, then insert a newline at the end
-    if (lex->chr0 == MP_LEXER_EOF) {
-        lex->chr0 = '\n';
-    } else if (lex->chr1 == MP_LEXER_EOF) {
-        if (lex->chr0 == '\r') {
-            lex->chr0 = '\n';
-        } else if (lex->chr0 != '\n') {
-            lex->chr1 = '\n';
-        }
-    } else if (lex->chr2 == MP_LEXER_EOF) {
-        if (lex->chr1 == '\r') {
-            lex->chr1 = '\n';
-        } else if (lex->chr1 != '\n') {
-            lex->chr2 = '\n';
-        }
-    }
+    // load lexer with start of file, advancing lex->column to 1
+    // start with dummy bytes and use next_char() for proper EOL/EOF handling
+    lex->chr0 = lex->chr1 = lex->chr2 = 0;
+    next_char(lex);
+    next_char(lex);
+    next_char(lex);
 
     // preload first token
     mp_lexer_to_next(lex);