From 16945c3c7af2c5c2a7a7e5cd35d23b340f92b1f0 Mon Sep 17 00:00:00 2001
From: Mario Fink <mario.fink@record-evolution.de>
Date: Fri, 12 Jul 2019 10:41:04 +0200
Subject: [PATCH] added function extract_all(...) for use in existing python
 script

---
 README.md        | 15 ++++++++++++++
 pytdm_ripper.pyx | 54 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 69 insertions(+)

diff --git a/README.md b/README.md
index 6d15f1d..26f61e0 100644
--- a/README.md
+++ b/README.md
@@ -78,3 +78,18 @@ wrapper.
   ```Shell
   python extract_all.py --help
   ```
+- The same functionality may be obtained from an existing python script by
+  importing the tdm_ripper module and calling the extract_all function. For
+  instance
+
+  ```Python
+  import tdm_ripper as td
+
+  td.extract_all(b"samples/SineData.tdm",b"samples/SineData.tdx",b"data/",b"my_tdm")
+  ```
+
+  where the arguments "data/" and "my_tdm" are optional. "data/" specifies the
+  directory where all .csv outout is dumped while "my_tdm" represents a name
+  prefix for all csv. files.
+  Note, that all string arguments must be converted to bytes before passing to
+  the argument list by prepending "b".
diff --git a/pytdm_ripper.pyx b/pytdm_ripper.pyx
index a658c4a..16b775c 100644
--- a/pytdm_ripper.pyx
+++ b/pytdm_ripper.pyx
@@ -1,6 +1,7 @@
 
 from tdm_ripper cimport tdm_ripper
 import numpy as np
+import re
 
 cdef class pytdmripper:
 
@@ -76,3 +77,56 @@ cdef class pytdmripper:
 
     def close(self):
         dummy = ""
+
+#-----------------------------------------------------------------------------#
+
+def extract_all(string tdmfile, string tdxfile, string outdirx = b"./", string prfxnam = b""):
+  """
+  Python function extracting all available data from .tdm and .tdx to .csv dump
+
+  Args:
+    tdmfile: path and filename of .tdm file
+    tdxfile: path and filename of associated .tdx file
+    outdirx: directory where all .csv output is dumped
+    prfxnam: optionally specify a name prefix for all .csv files
+
+  Return:
+    None
+  """
+
+  # TODO preliminary: assume utf-8
+  encoding = 'utf-8'
+
+  # set up instance of Cython ripper
+  td = pytdmripper(tdmfile,tdxfile)
+
+  # if no name prefix is given, .tdm filename will be used
+  prfx = ""
+  if prfxnam.decode(encoding) == prfx :
+      prfx = tdmfile.decode(encoding).rstrip('.tdm').split('/')[-1]
+  else:
+    prfx = prfxnam.decode(encoding)
+
+  # obtain number of available groups and channels
+  numgr = td.num_groups()
+  numch = td.num_channels()
+
+  # dump all meta information
+  td.print_meta((outdirx.decode(encoding)+prfx+'.csv').encode(encoding))
+
+  # dump all available groups and channels
+  for g in range(0,numgr):
+      numgrch = td.no_channels(g)
+      for c in range(0,numgrch):
+          # obtained overall channel id
+          chid = td.obtain_channel_id(g,c)
+          # get group's and channel's name
+          gname = td.group_name(g)
+          cname = td.channel_name(g,c)
+          # use regular expression replacement to sanitize group and channel names
+          gname = re.sub('[!@#$%^&*()-+= ,]','',gname)
+          cname = re.sub('[!@#$%^&*()-+= ,]','',cname)
+          # generate filename
+          fichan = prfx + '_' + str(g+1) + '_' + str(c+1) + '_' + gname + '_' + cname + '.csv'
+          # print channel
+          td.print_channel(chid,(outdirx.decode(encoding)+fichan).encode(encoding))