term: move the term core to subprojects/term

The core now builds, tests, and benchmarks alone, as a Meson subproject
with no dependency on the main tree.

- include/term/ holds term.h and the header-only unicode/. src/ holds
  the core and its private headers. The main tree gets only
  include/term through term_dep, so it cannot reach a private header.
- The term tests, the term benchmarks, the Kitty parser suite, and
  tools/amalgamate.py and tools/generate_unicode.py move with it. The
  tests run as term:<name>.
- The main build passes its -march (arch_flag) and b_ndebug to the
  subproject. A directory configured before this commit needs
  meson configure -Dterm:arch_flag=-march=... once.
- The term tests compile with -UNDEBUG. They do work inside assert.
- The subproject exports term_test_dep with term_api.h, for the main
  tree's render, thumbnail, color, and selection tests.
- The Kitty bridge used struct vector2i and has not compiled since the
  public API redesign. It builds again. 2 of its 14 tests fail: REP
  after a tab, and a cursor report after a resize.
- dirgraph.py drops the term and unicode layers. Its self-test uses pty.
- The symbols test ignores the __odr_asan symbols that ASan adds.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

1 files changed, 90 insertions, 0 deletions

diff --git a/src/text_run.h b/src/text_run.h
new file mode 100644
index 0000000..d546062
--- /dev/null
+++ b/src/text_run.h
@@ -0,0 +1,90 @@
+#ifndef TERM_TEXT_RUN_H
+#define TERM_TEXT_RUN_H
+
+#include "cell.h"
+#include "unicode/unicode.h"
+#include "unicode/grapheme.h"
+
+#define UTF8_LEAD_MIN 0xc2
+#define UTF8_LEAD_MAX 0xf4
+#define UTF8_LEAD3_TAG 0xE0
+#define UTF8_LEAD3_MASK 0xF0
+
+#define TERM_WIDTH_SLOTS 4
+struct width_cache {
+    uint32_t lo[TERM_WIDTH_SLOTS];
+    uint32_t span[TERM_WIDTH_SLOTS];
+    uint8_t klass;
+    uint8_t next;
+};
+
+/* term_new() builds the shared tables before any terminal can use them. */
+bool term_tables_ready(void);
+void term_text_tables_init(void);
+void term_snapshot_tables_init(void);
+
+int term_text_class(uint32_t cp);
+
+struct text_run_result {
+    int bytes;
+    int cols;
+    uint32_t last;
+};
+
+struct text_run_result term_text_run(struct cell *restrict row, const char *restrict buf,
+                                    int len, int max_cols, uint32_t fg, uint32_t bg,
+                                    uint32_t flags, uint32_t last, struct width_cache *restrict wc);
+
+struct text_run_bytes {
+    int bytes;          /* input used */
+    int cols;
+    int out;            /* bytes written */
+    int chars;
+    uint32_t last;
+    bool wide, narrow;  /* narrow: every character was one ASCII byte */
+};
+
+/* term_text_run() with the same rules, that writes the text in the history
+ * format instead of cells: raw UTF-8, a wide character after 0xF5. dst has
+ * room for 4 bytes per column. */
+struct text_run_bytes term_text_run_bytes(uint8_t *restrict dst, const char *restrict buf, int len,
+                                          int max_cols, uint32_t last, struct width_cache *restrict wc);
+
+static inline bool joins_cluster(uint32_t cp, int klass)
+{
+    if (cp < 0x0300)
+        return false;
+    if (klass == 0 || grapheme_emoji_modifier(cp))
+        return true;
+
+    return klass == 1 && unicode_spacing_mark(cp);
+}
+
+static inline bool can_extend_cluster(uint32_t last_char, uint32_t cp, int klass)
+{
+    if (klass == 0) return true;
+    if (last_char == 0x200D || grapheme_is_handle(last_char)) return true;
+    if (cp - 0x1F1E6u <= 0x19u && grapheme_regional_indicator(cp))
+        return true;
+    return joins_cluster(cp, klass);
+}
+
+static inline bool cluster_contextual(uint32_t cp)
+{
+    return unicode_spacing_mark(cp) || grapheme_emoji_modifier(cp) ||
+           (cp - 0x1F1E6u <= 0x19u && grapheme_regional_indicator(cp));
+}
+
+static inline bool cluster_joins(const uint32_t *cps, int len,
+                                 uint32_t cp, int klass)
+{
+    if (joins_cluster(cp, klass))
+        return true;
+    if (cps[len - 1] == 0x200D)
+        return unicode_extended_pictographic(cp);
+    return len == 1 && cp - 0x1F1E6u <= 0x19u &&
+           grapheme_regional_indicator(cp) &&
+           grapheme_regional_indicator(cps[0]);
+}
+
+#endif