hxltm-cli-xliff (#19), hxltm-cli-tmx (#20): improved documentation

README.md

@@ -457,6 +457,26 @@ pip install hdp-toolchain
 
 hxltmcli --help
 
+```
+
+**Advanced filter with HXL cli tools**
+- See **https://github.com/HXLStandard/libhxl-python/wiki/HXL-cookbook**
+
+```bash
+# libhxl already is installed with hdp-toolchain
+
+hxlselect --help
+#    Filter rows in a HXL dataset. (...)
+hxlcut --help
+#    Cut columns from a HXL dataset.
+
+## Examples with HXL TM (used before pass data to hxltmcli)
+hxlcut --exclude item+i_la+i_lat+is_Latn --sheet 6 HXL-CPLP-Vocab_Auxilium-Humanitarium-API.xlsx | hxltmcli
+# Excludes Latin before pass to hxltmcli, from Microsoft Excel
+
+hxlcut --exclude item+i_la+i_lat+is_Latn https://docs.google.com/spreadsheets/d/1ih3ouvx_n8W5ntNcYBqoyZ2NRMdaA0LRg5F9mGriZm4/edit#gid=1292720422 | hxltmcli
+# Excludes Latin before pass to hxltmcli, from Google Sheets
+
 ```
 ---
 
@@ -492,6 +512,14 @@ required).
 
 ```bash
 hxltmcli https://docs.google.com/spreadsheets/d/1ih3ouvx_n8W5ntNcYBqoyZ2NRMdaA0LRg5F9mGriZm4/edit#gid=1292720422
+#    (will print out contents of Google Sheets, without exporting to other formats)
+
+hxltmcli https://docs.google.com/spreadsheets/d/1ih3ouvx_n8W5ntNcYBqoyZ2NRMdaA0LRg5F9mGriZm4/edit#gid=1292720422 | grep UN_codicem_anglicum_IOM_HTCDS_nomen
+#    UN_codicem_anglicum_IOM_HTCDS_nomen,,,,13,1,UN,UN,codicem_anglicum,IOM,HTCDS,,,nomen,,,,,,,,,,,,,,∅,∅,Padrão de Dados de Casos de Tráfico Humano,∅,Revisão de texto requerida,Human Trafficking Case Data Standard,∅,∅,,∅,∅,,∅,∅,,∅,∅,,∅,∅
+
+hxltmcli https://docs.google.com/spreadsheets/d/1ih3ouvx_n8W5ntNcYBqoyZ2NRMdaA0LRg5F9mGriZm4/edit#gid=1292720422 schemam-un-htcds.tm.hxl.csv
+#    (Instead of print to stdout, save the contents to a single CSV file)
+
 ```
 
 **Write HXL TM data on Google Sheets**
@@ -514,6 +542,13 @@ required).
 # the Google Sheets entire groups of HXL TMs on 2021-06-29. New versions are
 # likely to be a different number than --sheet 6
 hxltmcli --sheet 6 HXL-CPLP-Vocab_Auxilium-Humanitarium-API.xlsx
+#    (will print out contents of --sheet 6, without exporting to other formats)
+
+hxltmcli --sheet 6 HXL-CPLP-Vocab_Auxilium-Humanitarium-API.xlsx | grep UN_codicem_anglicum_IOM_HTCDS_nomen
+#    UN_codicem_anglicum_IOM_HTCDS_nomen,,,,13,1,UN,UN,codicem_anglicum,IOM,HTCDS,,,nomen,,,,,,,,,,,,,,∅,∅,Padrão de Dados de Casos de Tráfico Humano,∅,Revisão de texto requerida,Human Trafficking Case Data Standard,∅,∅,,∅,∅,,∅,∅,,∅,∅,,∅,∅
+
+hxltmcli --sheet 6 HXL-CPLP-Vocab_Auxilium-Humanitarium-API.xlsx schemam-un-htcds.tm.hxl.csv
+#    (Instead of print to stdout, save the contents to a single CSV file)
 ```
 
 **Write HXL TM data on Microsoft Excel**

bin/hxltmcli

@@ -123,7 +123,8 @@ class HXLTMCLI:
             '--archivum-extensionem',
             help='File extension. .xlf, .csv or .tmx',
             action='store',
-            default='.xlf',
+            # default='.xlf',
+            default=None,
             nargs='?'
         )
 
@@ -210,21 +211,55 @@ class HXLTMCLI:
                 # print('tmx!')
                 self.hxltm2tmx(args.outfile, self.original_outfile,
                                self.original_outfile_is_stdout, args)
-            else:
-                # self.hxl2tab(args.outfile, self.original_outfile,
-                #              self.original_outfile_is_stdout, args)
-
+            elif args.archivum_extensionem == '.xliff' or args.archivum_extensionem == '.xlf':
+                # print('xliff!')
                 self.hxltm2csv(args.outfile, temp_csv4xliff.name,
                                False, args)
                 self.hxltm2xliff(temp_csv4xliff.name, self.original_outfile,
                                  self.original_outfile_is_stdout, args)
+            else:
+                # self.hxl2tab(args.outfile, self.original_outfile,
+                #              self.original_outfile_is_stdout, args)
+
+                # self.hxltm2csv(args.outfile, temp_csv4xliff.name,
+                #                False, args)
+                # print('noop')
+                self.hxltm2noop(args.outfile, self.original_outfile,
+                                self.original_outfile_is_stdout)
 
         finally:
             temp.close()
             temp_csv4xliff.close()
 
         return self.EXIT_OK
 
+    def hxltm2noop(self, hxlated_input, tab_output, is_stdout):
+        """
+        hxltm2noop only export whatever the initial HXL input was.
+
+        Requires that the input must be a valid HXLated file
+        """
+
+        with open(hxlated_input, 'r') as csv_file:
+            csv_reader = csv.reader(csv_file)
+
+            if is_stdout:
+                # txt_writer = csv.writer(sys.stdout, delimiter='\t')
+                txt_writer = csv.writer(sys.stdout)
+                # txt_writer.writerow(header_new)
+                for line in csv_reader:
+                    txt_writer.writerow(line)
+            else:
+
+                tab_output_cleanup = open(tab_output, 'w')
+                tab_output_cleanup.truncate()
+                tab_output_cleanup.close()
+
+                with open(tab_output, 'a') as new_txt:
+                    txt_writer = csv.writer(new_txt)
+                    for line in csv_reader:
+                        txt_writer.writerow(line)
+
     def hxltm2csv(self, hxlated_input, tab_output, is_stdout, args):
         """
         hxltm2csv pre-process the initial HXL TM on a intermediate format that