From dd676b78dd7a5fa871ac46af7bce18ebd18b0ec7 Mon Sep 17 00:00:00 2001
From: StarmanMartin <m.starman@live.com>
Date: Thu, 25 Jan 2024 15:15:40 +0100
Subject: [PATCH] feat: Tiff file reader. (#77)

Used Irregular tags which are parsed from the file
---
 converter_app/readers/__init__.py |  2 +
 converter_app/readers/tif.py      | 66 +++++++++++++++++++++++++++++++
 2 files changed, 68 insertions(+)
 create mode 100644 converter_app/readers/tif.py

diff --git a/converter_app/readers/__init__.py b/converter_app/readers/__init__.py
index de4cda64..96ab83db 100644
--- a/converter_app/readers/__init__.py
+++ b/converter_app/readers/__init__.py
@@ -23,6 +23,7 @@
 from .dwl import DWLReader
 from .ebl import EblReader
 from .cfx import CfxReader
+from .tif import TifReader
 from .jcamp_conv_reader import JcampReader
 from .pdf import PdfReader
 from .lithoz_pdf import PdfLithozReader
@@ -85,6 +86,7 @@ def match_reader(self, file):
 registry.register(DWLReader)
 registry.register(EblReader)
 registry.register(CfxReader)
+registry.register(TifReader)
 registry.register(JcampReader)
 registry.register(PdfReader)
 registry.register(PdfLithozReader)
diff --git a/converter_app/readers/tif.py b/converter_app/readers/tif.py
new file mode 100644
index 00000000..92a90d8d
--- /dev/null
+++ b/converter_app/readers/tif.py
@@ -0,0 +1,66 @@
+import logging
+import re
+from .base import Reader
+
+logger = logging.getLogger(__name__)
+
+UNIT_EXTENSION = "_unit"
+
+
+class TifReader(Reader):
+    identifier = 'tif_reader'
+    priority = 96
+    _parsed_values = None
+
+
+    def check(self):
+        result = False
+        if self.file.suffix.lower() == '.tif' and self.file.mime_type == 'image/tiff':
+            self._parsed_values = self._read_img()
+            result = self._parsed_values is not None and len(self._parsed_values) > 0
+        logger.debug('result=%s', result)
+        return result
+    def _read_img(self):
+        txt  = re.sub(r'\\x[0-9a-f]{2}', '', self.file.content.__str__())
+
+        txt = re.sub(r'^.+@@@@@@0\\r\\n', '', txt)
+        lines = re.split(r'\\r\\n', txt)
+        del lines[-1]
+        return [x.split('=') for x in lines]
+
+
+    def get_value(self, value):
+        if self.float_de_pattern.match(value):
+            # remove any digit group seperators and replace the comma with a period
+            return value.replace('.', '').replace(',', '.')
+        if self.float_us_pattern.match(value):
+            # just remove the digit group seperators
+            return value.replace(',', '')
+        else:
+            return None
+
+    def get_tables(self):
+        tables = []
+        table = self.append_table(tables)
+        for val in self._parsed_values:
+            if len(val) == 1:
+                num_val = self.get_value(val[0])
+                if num_val is not None:
+                    table['rows'].append([len(table['rows']), len(table['rows']), float(num_val)])
+            else:
+                table['metadata'][val[0]] = '='.join(val[1:])
+            table['header'].append(f"{'='.join(val)}")
+
+        table['columns'].append({
+            'key': '1',
+            'name': 'Idx'
+        })
+        table['columns'].append({
+            'key': '2',
+            'name': 'Number'
+        })
+
+        table['metadata']['rows'] = str(len(table['rows']))
+        table['metadata']['columns'] = str(len(table['columns']))
+
+        return tables