File size: 6,590 Bytes
58e6885
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
#!/usr/bin/env python3
import argparse
import csv
import json
import re
import subprocess
from pathlib import Path


ROOT = Path(__file__).resolve().parents[1]
TEMPLATE_ROOT = ROOT / "modules/chart_engine/template/d3-js"

CHECKS = {
    "missing_chart_utils": re.compile(r"chartUtils\."),
    "missing_color_resolver": re.compile(r"chartUtils\.color\.resolver"),
    "missing_schema_helper": re.compile(r"chartUtils\.schema\.(?:channel|channels|channelByKey|columns)"),
    "missing_format_helper": re.compile(r"chartUtils\.format\."),
    "missing_text_helper": re.compile(r"chartUtils\.text\."),
    "missing_legend_helper": re.compile(r"chartUtils\.legend\."),
}

ISSUE_PATTERNS = {
    "direct_column_index": re.compile(
        r"(?:dataColumns|data\.data\.columns|jsonData\.data\.columns)"
        r"\[[^\]]+\](?:\?\.|\.)"
        r"(?:name|role|unit|label|description|display_name|data_type|type)"
        r"|(?:dataColumns|data\.data\.columns|jsonData\.data\.columns)"
        r"\.(?:find|filter)\("
        r"|(?:dataColumns|data\.data\.columns|jsonData\.data\.columns)"
        r"\.filter\([^)]*\.role\s*===\s*['\"][^'\"]+['\"][^)]*\)\[[0-9]+\]\.name"
        r"|(?:dataColumns|data\.data\.columns|jsonData\.data\.columns)"
        r"\.find\([^)]*\.role\s*===\s*['\"][^'\"]+['\"][^)]*\)"
    ),
    "local_format_value": re.compile(r"\b(?:const|let|var|function)\s+formatValue\b|formatValue\s*="),
    "local_text_measure": re.compile(
        r"\b(?:const|let|var|function)\s+(?:getTextWidth|getTextWidthCanvas|measureText)\b"
        r"|\.getBBox\(|getComputedTextLength\(|\.measureText\("
    ),
    "local_parse_date": re.compile(
        r"\b(?:const|let|var|function)\s+parseDate\b|parseDate\s*="
        r"|new Date\(\s*d\[[^\]]+\]\s*\)"
    ),
    "direct_color_access": re.compile(
        r"\bcolors(?:\.|\?\.)"
        r"(?:other|field|available_colors|text_color|background_color)\b"
        r"|\b(?:data|jsonData|dataJSON)(?:\.|\?\.)colors(?:\.|\?\.)"
        r"(?:other|field|available_colors|text_color|background_color)\b"
    ),
    "direct_color_variant": re.compile(r"\.(?:brighter|darker)\("),
    "legacy_global_helper_call": re.compile(
        r"(?<![.\w$])(?:layoutLegend|getTextWidth|formatValue|parseDate)\("
    ),
    "debug_console_log": re.compile(r"console\.log\("),
    "math_random": re.compile(r"Math\.random\("),
    "schema_role_lookup": re.compile(
        r"\.(?:find|filter)\([^\n)]*\.role\s*={2,3}\s*['\"][^'\"]+['\"]"
        r"|(?:\b\w+|\])\.role\s*={2,3}\s*['\"][^'\"]+['\"]"
    ),
    "manual_legend": re.compile(
        r"\blegend(?:Group|G|Items?|Lines?|Container|Block|Offset|X|Y|Gap|Padding|Spacing|Width|Height)\b"
        r"|class[\"'],\s*[\"']legend"
    ),
}


def has_requirements(text: str) -> bool:
    return "REQUIREMENTS_BEGIN" in text and "REQUIREMENTS_END" in text


def node_check(path: Path) -> str:
    proc = subprocess.run(
        ["node", "--check", str(path)],
        stdout=subprocess.PIPE,
        stderr=subprocess.PIPE,
        text=True,
    )
    if proc.returncode == 0:
        return ""
    return proc.stderr.strip().splitlines()[0] if proc.stderr.strip() else "node --check failed"


def audit_file(path: Path, run_node_check: bool) -> dict:
    text = path.read_text(encoding="utf-8")
    record = {
        "path": str(path.relative_to(ROOT)),
        "has_requirements": has_requirements(text),
        "syntax_error": node_check(path) if run_node_check else "",
    }

    for name, pattern in CHECKS.items():
        if name.startswith("missing_"):
            record[name] = not bool(pattern.search(text))

    for name, pattern in ISSUE_PATTERNS.items():
        record[name] = bool(pattern.search(text))

    record["manual_legend_without_chart_utils_legend"] = (
        record["manual_legend"] and record["missing_legend_helper"]
    )
    return record


def summarize(records: list[dict]) -> dict:
    keys = [
        "has_requirements",
        "syntax_error",
        *CHECKS.keys(),
        *ISSUE_PATTERNS.keys(),
        "manual_legend_without_chart_utils_legend",
    ]
    summary = {"total_js": len(records)}
    summary["registered_requirement_files"] = sum(1 for record in records if record["has_requirements"])
    for key in keys:
        if key == "syntax_error":
            summary[key] = sum(1 for record in records if record[key])
        elif key == "has_requirements":
            continue
        else:
            summary[key] = sum(1 for record in records if record.get(key))
    return summary


def write_csv(path: Path, records: list[dict]) -> None:
    path.parent.mkdir(parents=True, exist_ok=True)
    fieldnames = list(records[0].keys()) if records else ["path"]
    with open(path, "w", newline="", encoding="utf-8") as f:
        writer = csv.DictWriter(f, fieldnames=fieldnames)
        writer.writeheader()
        writer.writerows(records)


def print_summary(summary: dict, records: list[dict], max_examples: int) -> None:
    print(json.dumps(summary, indent=2, ensure_ascii=False))
    for key, count in summary.items():
        if key in {"total_js", "registered_requirement_files"} or not count:
            continue
        examples = [record["path"] for record in records if record.get(key)][:max_examples]
        if examples:
            print(f"\n{key} examples:")
            for item in examples:
                print(f"  {item}")


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(description="Audit D3 template usage of chartUtils standard helpers.")
    parser.add_argument("--template-root", default=str(TEMPLATE_ROOT))
    parser.add_argument("--output-json", default=None)
    parser.add_argument("--output-csv", default=None)
    parser.add_argument("--examples", type=int, default=5)
    parser.add_argument("--node-check", action="store_true")
    return parser.parse_args()


def main() -> None:
    args = parse_args()
    template_root = Path(args.template_root)
    records = [
        audit_file(path, run_node_check=args.node_check)
        for path in sorted(template_root.rglob("*.js"))
    ]
    summary = summarize(records)

    if args.output_json:
        output_path = Path(args.output_json)
        output_path.parent.mkdir(parents=True, exist_ok=True)
        output_path.write_text(
            json.dumps({"summary": summary, "records": records}, indent=2, ensure_ascii=False),
            encoding="utf-8",
        )
    if args.output_csv:
        write_csv(Path(args.output_csv), records)

    print_summary(summary, records, args.examples)


if __name__ == "__main__":
    main()