ASPbases-python/getFileStructure.py at main · ninjamath3/ASPbases-python · GitHub

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
import tifffile
from datetime import datetime
import textwrap
import numpy as np
import importlib
import sys
import traceback

def dump_tiff_structure_to_txt(filepath, output_txt="tiff_structure.txt"):
    # Vérifie si imagecodecs est disponible
    has_imagecodecs = importlib.util.find_spec("imagecodecs") is not None
    if not has_imagecodecs:
        print("⚠️  Le module 'imagecodecs' n'est pas installé.")
        print("    → Certaines compressions (ex: LZW) ne pourront pas être décompressées.")
        print("    → Le script va continuer en ignorant la lecture des pixels.\n")

    with open(output_txt, "w", encoding="utf-8") as out:
        out.write(f"=== ANALYSE COMPLÈTE DU FICHIER TIFF ===\n")
        out.write(f"Fichier : {filepath}\n")
        out.write(f"Date d'analyse : {datetime.now()}\n")
        out.write("="*100 + "\n\n")

        with tifffile.TiffFile(filepath) as tif:
            out.write(f"Nombre total d’IFDs (images/pages) : {len(tif.pages)}\n")
            out.write(f"Ordre des octets : {'Little endian' if tif.byteorder == '<' else 'Big endian'}\n")
            out.write(f"BigTIFF : {'Oui' if tif.is_bigtiff else 'Non'}\n\n")
            out.write("="*100 + "\n")

            for i, page in enumerate(tif.pages):
                out.write(f"\n📄 IFD {i}\n")
                out.write("-"*100 + "\n")
                out.write(f"Dimensions              : {page.shape}\n")
                out.write(f"Dtype                   : {page.dtype}\n")
                out.write(f"Compression              : {getattr(page.compression, 'name', 'None')}\n")
                out.write(f"PhotometricInterpretation: {getattr(page.photometric, 'name', 'N/A')}\n")
                out.write(f"Samples per pixel        : {page.samplesperpixel}\n")
                out.write(f"Offset IFD               : {page.offset}\n")
                out.write(f"Planar configuration     : {getattr(page, 'planarconfig', 'N/A')}\n")
                out.write("\n--- TAGS INTERNES ---\n")

                # --- Lecture de tous les tags ---
                for tag in page.tags.values():
                    name = tag.name
                    dtype = tag.dtype.name if hasattr(tag, "dtype") else str(type(tag.value))
                    value = tag.value

                    # Tronquer les longues valeurs
                    if isinstance(value, (list, tuple, np.ndarray)) and len(value) > 15:
                        display_value = f"{value[:15]} ... ({len(value)} valeurs)"
                    else:
                        display_value = value

                    wrapped_value = "\n    ".join(textwrap.wrap(str(display_value), width=100))
                    out.write(f"{name:30s} | Type: {dtype:10s} | Valeur: {wrapped_value}\n")

                # --- Tags géospatiaux ---
                geo_tags = [
                    "ModelPixelScaleTag", "ModelTiepointTag",
                    "GeoKeyDirectoryTag", "GeoDoubleParamsTag", "GeoASCIIParamsTag"
                ]
                geo_present = [t for t in geo_tags if t in page.tags]
                if geo_present:
                    out.write("\n--- TAGS GÉOSPATIAUX ---\n")
                    for t in geo_present:
                        wrapped_geo = "\n    ".join(textwrap.wrap(str(page.tags[t].value), width=100))
                        out.write(f"{t:30s} : {wrapped_geo}\n")

                # --- Aperçu des données raster si possible ---
                out.write("\n--- EXTRAIT DES DONNÉES RASTER ---\n")
                if has_imagecodecs:
                    try:
                        data = page.asarray()
                        sample = data
                        if data.ndim == 2:
                            sample = data[:10, :10]
                        elif data.ndim == 3:
                            sample = data[0, :10, :10]
                        out.write(np.array2string(sample, threshold=100, max_line_width=120))
                        out.write("\n✅ Données raster extraites avec succès\n")
                    except Exception as e:
                        out.write(f"⚠️ Erreur lors de la lecture des données raster : {e}\n")
                        out.write(traceback.format_exc())
                else:
                    out.write("⏩ Lecture des pixels ignorée (module 'imagecodecs' non installé)\n")

                out.write("\n" + "-"*100 + "\n")

            out.write("\n=== FIN DE L'EXPLORATION ===\n")

    print(f"\n✅ Structure complète exportée dans : {output_txt}")

# ==============================
# Exécution principale
# ==============================
if __name__ == "__main__":
    dump_tiff_structure_to_txt(
        "data/2000-2022/GLC_FCS30D_20002022_W70S55_Annual.tif",
        "structure_tif_complete3.txt"
    )