version bump. Bring last modules from pmworker. Make mglib - tiff aware

changelog.md

@@ -1,11 +1,12 @@
 # Changelog
 
-## [1.2.0] - 16 July 2020
+## [1.2.1] - 16 July 2020
 
 ### Added
  
-  - shortcuts.extract_img - resizes/converts images jpg, png documents
-
+  - shortcuts.resize_img - resizes/converts images jpg, png documents
+  - change get_pagecount to work with tiff files as well
+  - bring in last modules from pmworker (mime and wrapper)
 
 ## [1.1.0] - 25 June 2020
 

mglib/mime.py

@@ -0,0 +1,40 @@
+import logging
+from pmworker import wrapper
+
+
+logger = logging.getLogger(__name__)
+
+
+class Mime(wrapper.Wrapper):
+    def __init__(self, filepath):
+        super().__init__(exec_name="file")
+        self.filepath = filepath
+
+    def get_cmd(self):
+        cmd = super().get_cmd()
+
+        cmd.extend(['--mime-type'])
+        cmd.extend(['-b'])
+        cmd.extend([self.filepath])
+
+        return cmd
+
+    def is_tiff(self):
+        return self.guess() == 'image/tiff'
+
+    def is_pdf(self):
+        return self.guess() == 'application/pdf'
+
+    def is_image(self):
+        """
+        Returns true if MIME type is one of following:
+            * image/png
+            * image/jpg
+        """
+        return self.guess() in ('image/png', 'image/jpg')
+
+    def guess(self):
+        cmd = self.get_cmd()
+        complete = self.run(cmd)
+
+        return complete.stdout.strip()

mglib/pdfinfo.py

@@ -11,6 +11,43 @@ small operations (e.g. get pdf page count).
 logger = logging.getLogger(__name__)
 
 
+def get_tiff_pagecount(filepath):
+    cmd = [
+        "/usr/bin/identify",
+        "-format",
+        "%n\n",
+        filepath
+    ]
+    compl = subprocess.run(
+        cmd,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE
+    )
+
+    if compl.returncode:
+
+        logger.error(
+            "get_tiff_pagecount: cmd=%s args=%s stdout=%s stderr=%s code=%s",
+            cmd,
+            compl.args,
+            compl.stdout,
+            compl.stderr,
+            compl.returncode,
+            stack_info=True
+        )
+
+        raise Exception("Error occured while getting document page count.")
+
+    lines = compl.stdout.decode('utf-8').split('\n')
+    # look up for the line containing "Pages: 11"
+    for line in lines:
+        x = re.match(r"(\d+)", line.strip())
+        if x:
+            return int(x.group(1))
+
+    return 0
+
+
 def get_pagecount(filepath):
     """
     Returns the number of pages in a PDF document as integer.
@@ -31,9 +68,12 @@ def get_pagecount(filepath):
         # considered by default one page document.
         return 1
 
-    if ext and ext.lower() not in ('.pdf',):
+    if ext and ext.lower() in ('.tiff', ):
+        return get_tiff_pagecount(filepath)
+
+    if ext and ext.lower() not in ('.pdf', '.tiff'):
         raise ValueError(
-            "Only jpeg, png and pdf are handlerd by this"
+            "Only jpeg, png, pdf and tiff are handlerd by this"
             " method"
         )
 

mglib/tiff.py

@@ -0,0 +1,32 @@
+import os
+import logging
+
+from mglib.runcmd import run
+
+logger = logging.getLogger(__name__)
+
+
+def convert_tiff2pdf(doc_url):
+
+    logger.debug(f"convert_tiff2pdf for {doc_url}")
+    # basename is filename + ext (no path)
+
+    basename = os.path.basename(doc_url)
+    base_root, base_ext = os.path.splitext(basename)
+    root, ext = os.path.splitext(doc_url)
+    new_doc_url = f"{root}.pdf"
+
+    logger.debug(
+        f"tiff2pdf source={doc_url} dest={new_doc_url}"
+    )
+
+    cmd = (
+        "convert",
+        doc_url,
+        new_doc_url,
+    )
+
+    run(cmd)
+
+    # returns new filename
+    return f"{base_root}.pdf"

mglib/wrapper.py

@@ -0,0 +1,49 @@
+import logging
+import subprocess
+
+logger = logging.getLogger(__name__)
+
+
+class Wrapper:
+
+    def __init__(self, exec_name, check=True, dry_run=False):
+        self.exec_name = exec_name
+        self.check = check,
+        # usefull for debugging purpose
+        self.dry_run = dry_run
+
+    def get_cmd(self):
+        cmd = []
+
+        if self.exec_name:
+            cmd.extend([self.exec_name])
+
+        return cmd
+
+    def call_no_args(self):
+
+        cmd = self.get_cmd()
+        self.run(cmd)
+
+    def run(self, cmd):
+
+        command_to_run = ' '.join(cmd)
+
+        if (self.dry_run):
+            logger.debug(f"Dry run: {command_to_run}")
+
+        logger.debug(f"subprocess: {command_to_run}")
+
+        ret = subprocess.run(
+            cmd,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            encoding="utf-8"
+        )
+        if ret.returncode != 0:
+            logger.error((
+                f"returncode={ret.returncode}"
+                f" stdout={ret.stdout}"
+                f" stderr={ret.stderr}"
+            ))
+        return ret

setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r") as fh:
 
 setup(
     name="mglib",
-    version="1.2.0",
+    version="1.2.1",
     author="Eugen Ciur",
     author_email="eugen@papermerge.com",
     url="https://github.com/papermerge/mglib",