port 2P step 1: vendor CPython 2.7.18 as the mtpython static library

The embedded 40250 script layer needs its own interpreter on five platforms. 2.7 is end-of-life, so nothing can be fetched from the target SDKs and the source is vendored (official 2.7.18 tarball, trimmed to 25MB; Lib/ stays for step 3's python27.zip). cpython-2.7.18/CMakeLists.txt builds one `mtpython` static library from exactly the 133 objects the reference libpython2.7.a contains, off by default behind -DMTGODOT_EMBED_PYTHON=ON. The source list and the built-in module table (config/config.c, 39 entries) are shared; pyconfig.h is a probe result and is not, so each platform keeps its own under config/<platform>/, regenerated by tools/py_embed/gen_pyconfig.sh and checked against the shared table. Three vendor patches, documented in docs/THIRD-PARTY.md: configure/configure.ac learn arm64 on macOS, and posixmodule.c undefines the process-control calls it hard-defines past pyconfig.h when building for iOS. macOS (ctest python.embed: every builtin imports, codecs and pickle work off the vendored Lib/), Android arm64 and iOS arm64 build. Linux needs a Linux host and Windows needs a MinGW-vs-MSVC decision; both are noted for step 4. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-23 08:27:35 +09:00
parent a9b31dec67
commit 5fad769ee8
1018 changed files with 652582 additions and 19 deletions
@@ -0,0 +1,132 @@
+/*
+ * _codecs_tw.c: Codecs collection for Taiwan's encodings
+ *
+ * Written by Hye-Shik Chang <perky@FreeBSD.org>
+ */
+
+#include "cjkcodecs.h"
+#include "mappings_tw.h"
+
+/*
+ * BIG5 codec
+ */
+
+ENCODER(big5)
+{
+    while (inleft > 0) {
+        Py_UNICODE c = **inbuf;
+        DBCHAR code;
+
+        if (c < 0x80) {
+            REQUIRE_OUTBUF(1)
+            **outbuf = (unsigned char)c;
+            NEXT(1, 1)
+            continue;
+        }
+        UCS4INVALID(c)
+
+        REQUIRE_OUTBUF(2)
+
+        TRYMAP_ENC(big5, code, c);
+        else return 1;
+
+        OUT1(code >> 8)
+        OUT2(code & 0xFF)
+        NEXT(1, 2)
+    }
+
+    return 0;
+}
+
+DECODER(big5)
+{
+    while (inleft > 0) {
+        unsigned char c = IN1;
+
+        REQUIRE_OUTBUF(1)
+
+        if (c < 0x80) {
+            OUT1(c)
+            NEXT(1, 1)
+            continue;
+        }
+
+        REQUIRE_INBUF(2)
+        TRYMAP_DEC(big5, **outbuf, c, IN2) {
+            NEXT(2, 1)
+        }
+        else return 2;
+    }
+
+    return 0;
+}
+
+
+/*
+ * CP950 codec
+ */
+
+ENCODER(cp950)
+{
+    while (inleft > 0) {
+        Py_UNICODE c = IN1;
+        DBCHAR code;
+
+        if (c < 0x80) {
+            WRITE1((unsigned char)c)
+            NEXT(1, 1)
+            continue;
+        }
+        UCS4INVALID(c)
+
+        REQUIRE_OUTBUF(2)
+        TRYMAP_ENC(cp950ext, code, c);
+        else TRYMAP_ENC(big5, code, c);
+        else return 1;
+
+        OUT1(code >> 8)
+        OUT2(code & 0xFF)
+        NEXT(1, 2)
+    }
+
+    return 0;
+}
+
+DECODER(cp950)
+{
+    while (inleft > 0) {
+        unsigned char c = IN1;
+
+        REQUIRE_OUTBUF(1)
+
+        if (c < 0x80) {
+            OUT1(c)
+            NEXT(1, 1)
+            continue;
+        }
+
+        REQUIRE_INBUF(2)
+
+        TRYMAP_DEC(cp950ext, **outbuf, c, IN2);
+        else TRYMAP_DEC(big5, **outbuf, c, IN2);
+        else return 2;
+
+        NEXT(2, 1)
+    }
+
+    return 0;
+}
+
+
+
+BEGIN_MAPPINGS_LIST
+  MAPPING_ENCDEC(big5)
+  MAPPING_ENCDEC(cp950ext)
+END_MAPPINGS_LIST
+
+BEGIN_CODECS_LIST
+  CODEC_STATELESS(big5)
+  CODEC_STATELESS(cp950)
+END_CODECS_LIST
+
+I_AM_A_MODULE_FOR(tw)