feat: implement S-52 TX TE text presentation

docs/报告/CM95_S52_TXTE文字后端阶段报告_v1.md

@@ -0,0 +1,28 @@
+# CM95 S-52 TX/TE 文字后端阶段报告 v1
+
+## 结论
+
+本阶段完成 S-52 `TX` / `TE` 到 PBF 标量字段与 MapLibre 通用文字层的闭环验证。
+
+- 全部 3057 条 Lookup 的文字物化异常：0。
+- Presentation Library 单条 Lookup 最多 3 个 TX/TE，因此固定三个文字 slot 可完整覆盖当前资源。
+- TX 参数形态统一为 9 参数，TE 统一为 10 参数。
+- 按 OpenCPN 实际代码确认 HJUST：1=center、2=right、3=left；VJUST：1=bottom、2=center、3=top。
+- XOFF 按平均字符宽度，YOFF 按字体高度处理。
+- 修正 CM93 `_texta` 结构化文本，使用其 `text` 字段，不再把 dict 字符串直接显示。
+## 福冈湾 v12 回归
+
+测试 tile：`z12/3531/1641`
+
+- Features：3293
+- Layers：23
+- hard_gate_unmapped：空
+- unresolved CSP：0
+- 产生通用 S-52 文字的 Feature：345
+- `_texto` 错误 dict 标签：0
+- Chrome / MapLibre 页面进入 READY；PBF、Sprite、Tile 正常加载。
+- 浏览器截图肉眼确认：泊位号、桥名、航标名、陆地区域名、海底底质等由 TX/TE 自动显示。
+
+测试页：`http://192.168.200.184:8877/presentation_v12.html?hud=collapsed`
+
+下一阶段：按全国实际命中量补 `LC` 复杂线型执行后端，然后继续 AP / vector-only symbol / 显示优先级。

src/cm95pbf/mapping.py

@@ -73,6 +73,7 @@ DELIVERY_PROPERTY_ALLOWLIST = frozenset(
         "s52_sector_sweep_deg",
         "s52_display_priority",
         "s52_lookup_rcid",
+        "s52_object_class",
         "s52_symbol_code",
         "s52_symbol_sequence",
         "s52_sounding_depth_m",
@@ -84,6 +85,40 @@ DELIVERY_PROPERTY_ALLOWLIST = frozenset(
         "s52_soundg_point_csp",
         "s52_table_name",
         "s52_text_literal",
+        "s52_text1_value",
+        "s52_text1_hjust",
+        "s52_text1_vjust",
+        "s52_text1_space",
+        "s52_text1_size",
+        "s52_text1_body_size",
+        "s52_text1_charspec",
+        "s52_text1_xoff",
+        "s52_text1_yoff",
+        "s52_text1_color",
+        "s52_text1_group",
+        "s52_text2_value",
+        "s52_text2_hjust",
+        "s52_text2_vjust",
+        "s52_text2_space",
+        "s52_text2_size",
+        "s52_text2_body_size",
+        "s52_text2_charspec",
+        "s52_text2_xoff",
+        "s52_text2_yoff",
+        "s52_text2_color",
+        "s52_text2_group",
+        "s52_text3_value",
+        "s52_text3_hjust",
+        "s52_text3_vjust",
+        "s52_text3_space",
+        "s52_text3_size",
+        "s52_text3_body_size",
+        "s52_text3_charspec",
+        "s52_text3_xoff",
+        "s52_text3_yoff",
+        "s52_text3_color",
+        "s52_text3_group",
+        "s52_text_count",
         "shape_class_code",
     }
 )

src/cm95pbf/presentation.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 from dataclasses import asdict, dataclass
+import re
 from typing import Any, Iterable
 
 
@@ -9,6 +10,131 @@ SUPPORTED_OPCODES = frozenset(
 )
 
 
+OPENCPN_NATSUR_TEXT = {
+    1: "mud", 2: "clay", 3: "silt", 4: "sand", 5: "stone",
+    6: "gravel", 7: "pebbles", 8: "cobbles", 9: "rock", 11: "lava",
+    14: "coral", 17: "shells", 18: "boulder", 51: "Wd", 56: "Bo",
+}
+
+
+def _strip_quotes(value: str) -> str:
+    text = str(value or "").strip()
+    if len(text) >= 2 and text[0] in {"'", '"'} and text[-1] == text[0]:
+        return text[1:-1]
+    return text
+
+
+def _resolve_text_param(value: str, attrs: dict[str, Any]) -> str:
+    raw = str(value or "").strip()
+    quoted = len(raw) >= 2 and raw[0] in {"'", '"'} and raw[-1] == raw[0]
+    if quoted:
+        return raw[1:-1]
+    if "=" in raw:
+        key, default = raw.split("=", 1)
+        current = attrs.get(key)
+        if current not in (None, ""):
+            return str(current)
+        return default.rstrip(")")
+    return raw.rstrip(")")
+
+
+def _text_attr_value(name: str, attrs: dict[str, Any]) -> str | None:
+    key = _strip_quotes(name)
+    if key not in attrs or attrs.get(key) in (None, ""):
+        return None
+    value = attrs.get(key)
+    if isinstance(value, dict):
+        text_value = value.get("text")
+        if text_value not in (None, ""):
+            return str(text_value)
+        return None
+    if key == "NATSUR":
+        values = value if isinstance(value, (list, tuple)) else str(value).split(",")
+        out = []
+        for item in values:
+            try:
+                out.append(OPENCPN_NATSUR_TEXT.get(int(item), "unk"))
+            except (TypeError, ValueError):
+                out.append("unk")
+        return ",".join(out)
+    if isinstance(value, (list, tuple)):
+        return ",".join(str(x) for x in value)
+    return str(value)
+
+
+def _format_te_value(fmt_raw: str, attr_raw: str, attrs: dict[str, Any]) -> str | None:
+    value = _text_attr_value(attr_raw, attrs)
+    if value is None:
+        return None
+    fmt = _strip_quotes(fmt_raw).replace("lf", "f")
+    match = re.search(r"%(?:[-+0 #]*\d*(?:\.\d+)?)?([csfdi])", fmt)
+    try:
+        if match is None:
+            return fmt
+        conversion = match.group(1)
+        if conversion == "f":
+            return fmt % float(value)
+        if conversion in {"d", "i"}:
+            return fmt % int(float(value))
+        if conversion == "c":
+            return fmt % (int(float(value)) if str(value).lstrip("+-").isdigit() else str(value)[0])
+        return fmt % value
+    except (TypeError, ValueError, IndexError):
+        return None
+
+
+def materialize_text_hints(instruction: str, attrs: dict[str, Any]) -> dict[str, Any]:
+    """Materialize OpenCPN-compatible TX/TE rules into at most three text slots."""
+    out: dict[str, Any] = {}
+    slot = 0
+    for rule in parse_instruction_string(instruction):
+        if rule.opcode not in {"TX", "TE"}:
+            continue
+        args = rule.args
+        if rule.opcode == "TX":
+            if len(args) < 9:
+                continue
+            first = str(args[0]).strip()
+            if len(first) >= 2 and first[0] in {"'", '"'} and first[-1] == first[0]:
+                text = _strip_quotes(first)
+            else:
+                text = _text_attr_value(first, attrs)
+            layout = args[1:9]
+        else:
+            if len(args) < 10:
+                continue
+            text = _format_te_value(args[0], args[1], attrs)
+            layout = args[2:10]
+        if text in (None, ""):
+            continue
+        slot += 1
+        if slot > 3:
+            break
+        prefix = f"s52_text{slot}_"
+        out[prefix + "value"] = str(text)
+        out[prefix + "hjust"] = _resolve_text_param(layout[0], attrs)
+        out[prefix + "vjust"] = _resolve_text_param(layout[1], attrs)
+        out[prefix + "space"] = _resolve_text_param(layout[2], attrs)
+        charspec = _resolve_text_param(layout[3], attrs)
+        out[prefix + "charspec"] = charspec
+        if len(charspec) >= 4 and charspec[3:].isdigit():
+            body_size = int(charspec[3:])
+            out[prefix + "body_size"] = body_size
+            # OpenCPN normalizes S-52 body size to the user ChartText base
+            # instead of rendering 18/20 as literal pixel sizes.  Use a
+            # deterministic 10px web base; a future NavSea text-scale setting
+            # can shift this derived size without losing the raw body size.
+            normalized = int((min(20, max(0, body_size)) / 20.0) * 4.0)
+            out[prefix + "size"] = max(10, 10 + normalized)
+        out[prefix + "xoff"] = _resolve_text_param(layout[4], attrs)
+        out[prefix + "yoff"] = _resolve_text_param(layout[5], attrs)
+        out[prefix + "color"] = _resolve_text_param(layout[6], attrs)
+        out[prefix + "group"] = _resolve_text_param(layout[7], attrs)
+    if slot:
+        out["s52_text_count"] = slot
+    return out
+
+
 class PresentationParseError(ValueError):
     pass
 

src/cm95pbf/s52.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import Any, Iterable
 
-from .presentation import static_rule_hints
+from .presentation import materialize_text_hints, static_rule_hints
 from .csp import S52MarinerSettings, resolve_csp_hints
 
 
@@ -438,6 +438,7 @@ class S52LookupRegistry:
             "s52_table_name": str(row.get("table_name") or ""),
         }
         out.update(dict(row.get("_static_hints") or {}))
+        out.update(materialize_text_hints(str(row.get("instruction") or ""), normalized_attrs))
         if lookup_class != str(object_class):
             out["s52_object_class"] = lookup_class
         procedures = [

tools/cm95_s52_full_database_audit.py

@@ -114,6 +114,12 @@ def main() -> int:
     unsupported_csp_counts = Counter()
     opcode_counts = Counter()
     direct_symbol_counts = Counter()
+    pattern_counts = Counter()
+    complex_line_counts = Counter()
+    area_color_counts = Counter()
+    simple_line_counts = Counter()
+    tx_rule_counts = Counter()
+    te_rule_counts = Counter()
     substitution_counts = Counter()
 
     sql = (
@@ -165,7 +171,19 @@ def main() -> int:
                     opcode_counts[opcode] += 1
                 args_list = rule.get("args") or []
                 if opcode == "SY" and args_list:
-                    direct_symbol_counts[str(args_list[0])[:8]] += 1
+                    direct_symbol_counts[str(args_list[0]).strip("'\"")[:8]] += 1
+                elif opcode == "AP" and args_list:
+                    pattern_counts[str(args_list[0]).strip("'\"")[:8]] += 1
+                elif opcode == "LC" and args_list:
+                    complex_line_counts[str(args_list[0]).strip("'\"")[:8]] += 1
+                elif opcode == "AC" and args_list:
+                    area_color_counts[str(args_list[0]).strip("'\"")] += 1
+                elif opcode == "LS" and len(args_list) >= 3:
+                    simple_line_counts[tuple(str(x).strip("'\"") for x in args_list[:3])] += 1
+                elif opcode == "TX":
+                    tx_rule_counts[tuple(str(x) for x in args_list)] += 1
+                elif opcode == "TE":
+                    te_rule_counts[tuple(str(x) for x in args_list)] += 1
                 if opcode == "CS" and args_list:
                     name = str(args_list[0])[:8]
                     csp_counts[name] += 1
@@ -202,6 +220,13 @@ def main() -> int:
         "implemented_csp_counts": dict(implemented_csp_counts),
         "unsupported_csp_counts": dict(unsupported_csp_counts),
         "direct_symbol_top100": direct_symbol_counts.most_common(100),
+        "symbol_resource_counts": direct_symbol_counts.most_common(),
+        "pattern_resource_counts": pattern_counts.most_common(),
+        "complex_line_resource_counts": complex_line_counts.most_common(),
+        "area_color_counts": area_color_counts.most_common(),
+        "simple_line_rule_counts": [[list(k), v] for k, v in simple_line_counts.most_common()],
+        "tx_rule_counts": [[list(k), v] for k, v in tx_rule_counts.most_common()],
+        "te_rule_counts": [[list(k), v] for k, v in te_rule_counts.most_common()],
         "class_substitution_counts": [
             {"source_object_class": k[0], "s52_object_class": k[1], "geometry_type": k[2], "count": v}
             for k, v in substitution_counts.most_common()