From 61c35bd545b70fb8102b82465577a3efd7888bbf Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Fri, 3 Dec 2021 13:17:12 +0100
Subject: [PATCH 01/35] fix MODS name without roles, ht@kba #51

---
 mets_mods2tei/api/mets.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 56359ba..b7a0eab 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -145,7 +145,7 @@ def __spur(self):
                 person[name_part.get_type()] = name_part.get_valueOf_()
 
             # either author or editor
-            roles = name.get_role()[0].get_roleTerm()
+            roles = name.get_role()[0].get_roleTerm() if name.get_role() else []
             # TODO: handle the complete set of allowed roles
             for role in roles:
                 if role.get_valueOf_() == "edt":

From 499c3ccc064c3e5b1c7c4f70dade68bed100f11a Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Fri, 3 Dec 2021 15:27:59 +0100
Subject: [PATCH 02/35] fallback to empty publicationStmt/date and encodingDesc
 if metsHdr is missing

---
 mets_mods2tei/api/mets.py | 26 ++++++++++++++++++++------
 mets_mods2tei/api/tei.py  |  8 +++++---
 2 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index b7a0eab..351f93f 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -237,12 +237,26 @@ def __spur(self):
         #
         # metsHdr
         header = self.mets.get_metsHdr()
-
-        # encoding date
-        self.encoding_date = header.get_CREATEDATE().isoformat()
-
-        # encoding description
-        self.encoding_desc = list(filter(lambda x: x.get_OTHERTYPE() == "SOFTWARE", header.get_agent()))[0].get_name()
+        if header:
+            # encoding date
+            self.encoding_date = header.get_CREATEDATE()
+            # encoding description
+            self.encoding_desc = [agent.get_name()
+                                  for agent in header.get_agent()
+                                  if agent.get_TYPE() == "OTHER" and agent.get_OTHERTYPE() == "SOFTWARE"]
+        else:
+            self.encoding_date = None
+            self.encoding_desc = None
+        
+        if self.encoding_date:
+            self.encoding_date = self.encoding_date.isoformat()
+        else:
+            self.logger.error("Found no @CREATEDATE for publicationStmt/date")
+        if self.encoding_desc:
+            self.encoding_desc = self.encoding_desc[0] # or -1?
+            # what about agent.get_OTHERROLE() and agent.get_note()?
+        else:
+            self.logger.error("Found no mets:agent for encodingDesc")
 
 	#
 	# location of manuscript
diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index 741e72b..6a4d260 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -462,15 +462,17 @@ def add_encoding_date(self, date):
         publication_stmt = self.tree.xpath('//tei:publicationStmt', namespaces=ns)[0]
         encoding_date = etree.SubElement(publication_stmt, "%sdate" % TEI)
         encoding_date.set("type", "publication")
-        encoding_date.text = date
+        if date:
+            encoding_date.text = date
 
     def set_encoding_description(self, creator):
         """
         Set some details on the encoding of the digital edition
         """
         encoding_desc = self.tree.xpath('//tei:encodingDesc', namespaces=ns)[0]
-        encoding_desc_details = etree.SubElement(encoding_desc, "%sp" % TEI)
-        encoding_desc_details.text = "Encoded with the help of %s." % creator
+        if creator:
+            encoding_desc_details = etree.SubElement(encoding_desc, "%sp" % TEI)
+            encoding_desc_details.text = "Encoded with the help of %s." % creator
 
     def add_repository(self, repository):
         """

From 8984b1b0c52c2981a55cf53f375c1db877e5409d Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Fri, 3 Dec 2021 17:10:26 +0100
Subject: [PATCH 03/35] get_text_in_line: append HYP content if available

---
 mets_mods2tei/api/alto.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/mets_mods2tei/api/alto.py b/mets_mods2tei/api/alto.py
index e1a2cec..4da9af9 100644
--- a/mets_mods2tei/api/alto.py
+++ b/mets_mods2tei/api/alto.py
@@ -92,7 +92,11 @@ def get_text_in_line(self, line):
         Returns the ALTO-encoded text .
         :param Element line: The line to extract the text from.
         """
-        return " ".join(element.get("CONTENT") for element in line.xpath("./alto:String", namespaces=ns))
+        text = " ".join(element.get("CONTENT") for element in line.xpath("./alto:String", namespaces=ns))
+        hyp = line.find("alto:HYP", namespaces=ns)
+        if hyp is not None:
+            text += hyp.get("CONTENT")
+        return text
 
     def __compute_fuzzy_distance(self, text1, text2):
         """

From 7b136c8603587c5bd3c323f467e645aebc57637c Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Fri, 3 Dec 2021 17:11:06 +0100
Subject: [PATCH 04/35] log to stderr instead of stdout (to prevent mixing with
 TEI)

---
 README.md                              | 2 +-
 mets_mods2tei/scripts/mets_mods2tei.py | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 63df7e0..2df14b2 100644
--- a/README.md
+++ b/README.md
@@ -118,5 +118,5 @@ including the extracted information from the MODS part of the METS.
 
 Example:
 
-    mm2tei "https://digital.slub-dresden.de/oai/?verb=GetRecord&metadataPrefix=mets&identifier=oai:de:slub-dresden:db:id-453779263"
+    mm2tei "https://digital.slub-dresden.de/oai/?verb=GetRecord&metadataPrefix=mets&identifier=oai:de:slub-dresden:db:id-453779263" > tei.xml
 
diff --git a/mets_mods2tei/scripts/mets_mods2tei.py b/mets_mods2tei/scripts/mets_mods2tei.py
index 28a3bdc..35e4b1e 100644
--- a/mets_mods2tei/scripts/mets_mods2tei.py
+++ b/mets_mods2tei/scripts/mets_mods2tei.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 
+import sys
 import os
 import logging
 import click
@@ -19,7 +20,7 @@ def cli(mets, ocr, text_group, log_level):
 
     #
     # logging level
-    logging.basicConfig(level=logging.getLevelName(log_level))
+    logging.basicConfig(level=logging.getLevelName(log_level), stream=sys.stderr)
     
     #
     # interpret mets argument

From 6545b162aacbcc173fe03c1e093fc914b9f87f68 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Fri, 3 Dec 2021 18:20:27 +0100
Subject: [PATCH 05/35] improve makefile

---
 Makefile | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index fdc422a..3750276 100644
--- a/Makefile
+++ b/Makefile
@@ -1,5 +1,6 @@
 # Python interpreter. Default: '$(PYTHON)'
-PYTHON = python
+PYTHON ?= python
+PIP ?= pip
 
 # BEGIN-EVAL makefile-parser --make-help Makefile
 
@@ -7,12 +8,16 @@ help:
 	@echo ""
 	@echo "  Targets"
 	@echo ""
+	@echo "    install   Install this package"
+	@echo "    deps      Install dependencies only"
+	@echo "    deps-test Install dependencies for testing only"
 	@echo "    test      Run all unit tests"
 	@echo "    coverage  Run coverage tests"
 	@echo ""
 	@echo "  Variables"
 	@echo ""
 	@echo "    PYTHON  Python interpreter. Default: '$(PYTHON)'"
+	@echo "    PIP     Python packager. Default: '$(PIP)'"
 
 # END-EVAL
 
@@ -20,7 +25,16 @@ help:
 # Tests
 #
 
-.PHONY: test coverage
+.PHONY: install test coverage deps deps-test
+
+install:
+	$(PIP) install .
+
+deps:
+	$(PIP) install -r requirements.txt
+
+deps-test:
+	$(PIP) install -r requirements-test.txt
 
 # Run all unit tests
 test:

From 711025a833d46f4e9c0ab8b065dc25e9c72ab803 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Fri, 3 Dec 2021 18:47:57 +0100
Subject: [PATCH 06/35] improve CI

---
 .circleci/config.yml | 45 +++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 40 insertions(+), 5 deletions(-)

diff --git a/.circleci/config.yml b/.circleci/config.yml
index 30a331e..668e893 100644
--- a/.circleci/config.yml
+++ b/.circleci/config.yml
@@ -1,19 +1,54 @@
 # Python CircleCI 2.1 configuration file
 # for mets-mods2tei
 #
-# Check https://circleci.com/docs/2.1/language-python/ for more details
+# Check https://circleci.com/docs/2.0/language-python/ for more details
 #
 version: 2.1
 orbs:
   codecov: codecov/codecov@1.0.5
 jobs:
-  build:
+  test:
+    parameters:
+      version:
+        type: string
     docker:
-      - image: python:3.6
+      - image: circleci/python:<< parameters.version >>
     working_directory: ~/repo
     steps:
       - checkout
-      - run: pip install -r requirements-test.txt
-      - run: pip install .
+      - run: make deps deps-test
+      - run: make install
+      - run: make test
       - run: make coverage
       - codecov/upload
+  pypi:
+    docker:
+      - image: circleci/python:3.6
+    working_directory: ~/repo
+    steps:
+      - checkout
+      - setup_remote_docker
+      - run: make install
+      - run: python setup.py sdist
+      - run: |
+          pip install cibuildwheel
+          cibuildwheel --output-dir dist
+      - store_artifacts:
+          path: dist/
+          destination: artifacts
+    # later: upload to PyPI...
+
+workflows:
+  version: 2
+  test-all:
+    jobs:
+      - test:
+          matrix:
+            parameters:
+              version: [3.5.10, 3.6.15, 3.7.12, 3.8.12, 3.9.9]
+  deploy:
+    jobs:
+      - pypi:
+          filters:
+            branches:
+              only: master

From 605dd898b597ae242858edf34f2da720a489a916 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sun, 5 Dec 2021 01:04:46 +0100
Subject: [PATCH 07/35] mets.fromfile: allow missing logical structmap

---
 mets_mods2tei/api/mets.py | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 351f93f..a503d2d 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -123,10 +123,9 @@ def __spur(self):
 
         #
         # main title and manuscript type
-        struct_map_logical = list(filter(lambda x: x.get_TYPE() == "LOGICAL", self.mets.get_structMap()))[0]
-        title = struct_map_logical.get_div()
-        self.title = title.get_LABEL()
-        self.type = title.get_TYPE()
+        div = self.get_div_structure()
+        self.title = div.get_LABEL() if div else ""
+        self.type = div.get_TYPE() if div else ""
 
         #
         # sub titles

From 3bfa7c265488c5043c213e2adadb9ec0813a1802 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sun, 5 Dec 2021 01:05:46 +0100
Subject: [PATCH 08/35] mets.fromfile: allow missing mods originInfo

---
 mets_mods2tei/api/mets.py | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index a503d2d..1fc8a38 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -154,29 +154,34 @@ def __spur(self):
 
         #
         # orgin info
-        origin_info = self.mods.get_originInfo()[0]
+        origin_info = self.mods.get_originInfo()
 
         # publication place
         self.places = []
-        for place in origin_info.get_place():
-            place_ext = {}
-            for place_term in place.get_placeTerm():
-                place_ext[place_term.get_type()] = place_term.get_valueOf_()
-            self.places.append(place_ext)
+        if origin_info:
+            for place in origin_info[0].get_place():
+                place_ext = {}
+                for place_term in place.get_placeTerm():
+                    place_ext[place_term.get_type()] = place_term.get_valueOf_()
+                self.places.append(place_ext)
 
         # publication dates
         self.dates = {}
-        for date_issued in origin_info.get_dateIssued():
-            date_type = date_issued.get_point() if date_issued.get_point() != None else "unspecified"
-            self.dates[date_type] = date_issued.get_valueOf_()
+        if origin_info:
+            for date_issued in origin_info[0].get_dateIssued():
+                date_type = date_issued.get_point() if date_issued.get_point() != None else "unspecified"
+                self.dates[date_type] = date_issued.get_valueOf_()
 
         # publishers
         self.publishers = []
-        for publisher in origin_info.get_publisher():
-            self.publishers.append(publisher.get_valueOf_())
+        if origin_info:
+            for publisher in origin_info[0].get_publisher():
+                self.publishers.append(publisher.get_valueOf_())
 
         # edition of the manuscript
-        self.edition = origin_info.get_edition()[0].get_valueOf_() if origin_info.get_edition() else ""
+        self.edition = ""
+        if origin_info and origin_info[0].get_edition():
+            self.edition = origin_info[0].get_edition()[0].get_valueOf_()
 
         #
         # languages and scripts

From 559e4c1f02916a2b6a2a514c0c9d5741beef61ff Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sun, 5 Dec 2021 01:07:42 +0100
Subject: [PATCH 09/35] mets.fromfile: allow missing mods physicalDescription

---
 mets_mods2tei/api/mets.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 1fc8a38..88d004e 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -205,15 +205,18 @@ def __spur(self):
 
         #
         # physical description
-        physical_description = self.mods.get_physicalDescription()[0]
+        physical_description = self.mods.get_physicalDescription()
 
         # digital origin
-        self.digital_origin = physical_description.get_digitalOrigin()[0] if physical_description.get_digitalOrigin() else ""
+        self.digital_origin = ""
+        if physical_description and physical_description[0].get_digitalOrigin():
+            self.digital_origin = physical_description[0].get_digitalOrigin()[0]
 
         # extent
         self.extents = []
-        for extent in physical_description.get_extent():
-            self.extents.append(extent.get_valueOf_())
+        if physical_description:
+            for extent in physical_description[0].get_extent():
+                self.extents.append(extent.get_valueOf_())
 
         #
         # dv FIXME: replace with generated code as soon as schema is available

From 1a7fe59038bed7228e381de244cb5593e77d48a0 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sun, 5 Dec 2021 01:08:20 +0100
Subject: [PATCH 10/35] mets.fromfile: allow missing mets amdSec provenance dv

---
 mets_mods2tei/api/mets.py | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 88d004e..9da0496 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -220,16 +220,20 @@ def __spur(self):
 
         #
         # dv FIXME: replace with generated code as soon as schema is available
-        dv = etree.fromstring(self.mets.get_amdSec()[0].get_rightsMD()[0].get_mdWrap().get_xmlData().get_anytypeobjs_()[0])
+        amdsec = self.mets.get_amdSec()
+        if amdsec and amdsec[0].get_rightsMD():
+            dv = etree.fromstring(amdsec[0].get_rightsMD()[0].get_mdWrap().get_xmlData().get_anytypeobjs_()[0])
+        else:
+            dv = []
 
         # owner of the digital edition
-        self.owner_digital = dv.xpath("//dv:owner", namespaces=ns)[0].text
+        self.owner_digital = dv.xpath("//dv:owner", namespaces=ns)[0].text if dv else ""
 
         # availability/license
         # common case
         self.license = ""
         self.license_url = ""
-        license_nodes = dv.xpath("//dv:license", namespaces=ns)
+        license_nodes = dv.xpath("//dv:license", namespaces=ns) if dv else []
         if license_nodes != []:
             self.license = license_nodes[0].text
             self.license_url = ""

From af1740e07afddf9bf0533f517777fa324aca5060 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sun, 5 Dec 2021 01:09:40 +0100
Subject: [PATCH 11/35] mets.fromfile: simplify physical struct map, allow
 missing @ORDER

---
 mets_mods2tei/api/mets.py | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 9da0496..409cea6 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -52,6 +52,7 @@ def __init__(self):
         self.tree = None
         self.mets = None
         self.mods = None
+        self.page_map = {}
         self.order_map = {}
         self.img_map = {}
         self.alto_map = {}
@@ -319,8 +320,10 @@ def __spur(self):
                 default_map[entry.get("ID")] = entry.find("./" + METS + "FLocat").get("%shref" % XLINK)
 
         # struct map physical
-        for div in list(filter(lambda x: x.get_TYPE() == 'PHYSICAL', self.mets.get_structMap()))[0].get_div().get_div():
-            self.order_map[div.get_ID()] = div.get_ORDER()
+        for div in self.get_page_structure().get_div():
+            self.page_map[div.get_ID()] = div
+            if div.get_ORDER():
+                self.order_map[div.get_ID()] = div.get_ORDER()
             for fptr in div.get_fptr():
                 if fptr.get_FILEID() in fulltext_map:
                     self.alto_map[div.get_ID()] = fulltext_map[fptr.get_FILEID()]
@@ -472,6 +475,15 @@ def get_languages(self):
         """
         return self.languages
 
+    def get_page_structure(self):
+        """
+        Return the div structure from the physical struct map
+        """
+        for struct_map in self.mets.get_structMap():
+            if struct_map.get_TYPE() == "PHYSICAL":
+                return struct_map.get_div()
+        return None
+
     def get_div_structure(self):
         """
         Return the div structure from the logical struct map

From 18a2ddeafe9df312c7dc5ff51f05114fcd699c21 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sun, 5 Dec 2021 01:10:34 +0100
Subject: [PATCH 12/35] mets.fromfile: allow missing struct link

---
 mets_mods2tei/api/mets.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 409cea6..d8f107b 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -331,7 +331,8 @@ def __spur(self):
                     self.img_map[div.get_ID()] = default_map[fptr.get_FILEID()]
 
         # struct links
-        for sm_link in self.tree.xpath("//mets:structLink", namespaces=ns)[0].iterchildren():
+        structlinks = self.tree.xpath("//mets:structLink/*", namespaces=ns)
+        for sm_link in structlinks:
             if sm_link.get("%sto" % XLINK) in self.alto_map:
                 if sm_link.get("%sfrom" % XLINK) not in self.struct_links:
                     self.struct_links[sm_link.get("%sfrom" % XLINK)] = []

From dbcc1feb9fc0d2310228423981c6402373e1f23f Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sun, 5 Dec 2021 01:11:44 +0100
Subject: [PATCH 13/35] teil.fill_from_mets: allow empty logical struct map and
 struct link

(fall back to physical pages, sorted if possible, or error with empty text)
---
 mets_mods2tei/api/mets.py |  2 +-
 mets_mods2tei/api/tei.py  | 34 ++++++++++++++++++++++++++--------
 2 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index d8f107b..18fa66c 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -492,7 +492,7 @@ def get_div_structure(self):
         for struct_map in self.mets.get_structMap():
             if struct_map.get_TYPE() == "LOGICAL":
                 return struct_map.get_div()
-        return []
+        return None
 
     def get_struct_links(self, log_id):
         """
diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index 6a4d260..f9ce804 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -132,7 +132,18 @@ def fill_from_mets(self, mets, ocr=True):
         # text part
 
         # div structure
-        self.add_div_structure(mets.get_div_structure())
+        div = mets.get_div_structure()
+        if div is not None:
+            self.logger.info("Found logical structMap for %s", div.get_TYPE())
+            self.add_div_structure(div)
+        elif any(mets.alto_map):
+            self.logger.warning("Found no logical structMap div, falling back to physical")
+            pages = mets.alto_map.keys()
+            if any(mets.order_map.values()):
+                pages = sorted(pages, key=mets.get_order)
+            self.add_div_structure(None, map(mets.page_map.get, pages))
+        else:
+            self.logger.error("Found no logical or physical structMap div")
 
         # OCR
         if ocr:
@@ -597,6 +608,9 @@ def __add_ocr_to_node(self, node, mets):
         for childnode in node.iterchildren():
             self.__add_ocr_to_node(childnode, mets)
         struct_links = mets.get_struct_links(node.get("id"))
+        if not struct_links and node.get("id") in mets.page_map:
+            # already physical
+            struct_links = [node.get("id")]
         
         # a header will always be on the first page of a div
         first = True
@@ -678,15 +692,23 @@ def __add_ocr_to_node(self, node, mets):
                             node.insert(0, par)
             first = False
 
-    def add_div_structure(self, div):
+    def add_div_structure(self, div, pages=None):
         """
-        Add div elements to the text body according to the given list of divs
+        Add logical div elements to the text font/body/back according to the given div hierarchy
         """
 
         # div structure has to be added to text
         text = self.tree.xpath('//tei:text', namespaces=ns)[0]
+        front = etree.SubElement(text, "%sfront" % TEI)
+        body = etree.SubElement(text, "%sbody" % TEI)
+        back = etree.SubElement(text, "%sback" % TEI)
+
+        if pages:
+            for page in pages:
+                self.__add_div(body, page, 1)
+            return
 
-        # decent to the deepest AMD
+        # descend to the deepest AMD
         while div.get_ADMID() is None:
             div = div.get_div()[0]
         start_div = div.get_div()[0]
@@ -694,10 +716,6 @@ def add_div_structure(self, div):
             div = start_div
             start_div = start_div.get_div()[0]
         
-        front = etree.SubElement(text, "%sfront" % TEI)
-        body = etree.SubElement(text, "%sbody" % TEI)
-        back = etree.SubElement(text, "%sback" % TEI)
-
         entry_point = front
 
         for sub_div in div.get_div():

From 61c46249b4f08f5c17a65a510f9fab425b8cfd18 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sun, 5 Dec 2021 01:13:48 +0100
Subject: [PATCH 14/35] METS to TEI structure: comment urging for more+better
 mappings

---
 mets_mods2tei/api/tei.py | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index f9ce804..a46a7b1 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -724,8 +724,48 @@ def add_div_structure(self, div, pages=None):
             elif sub_div.get_TYPE() == "title_page":
                 self.__add_div(entry_point, sub_div, 1, "titlePage")
             else:
+                # FIXME: if title_page gets preceded by figure/preface/contents/..., they *all* will end up in body
                 entry_point = body
                 self.__add_div(entry_point, sub_div, 1)
+            # FIXME: add more structural mappings from METS-Anwendungsprofil (DFG Strukturdatenset) to TEI-P5 tagset (DTAbf)
+            # ...for example:
+            # contents → contents
+            # corrigenda → corrigenda
+            # dedication → dedication
+            # index → index
+            # imprint → imprint
+            # ? → imprimatur
+            # priviledges? → copyright
+            # provenance → ?
+            # ? → appendix
+            # ? → advertisement
+            # preface → preface
+            # ? → postface
+            # chapter → chapter
+            # letter → letter
+            # verse → poem
+            # ? → diaryEntry
+            # ? → recipe
+            # ? → scene
+            # ? → act
+            # ? → frontispiece
+            # ? → bibliography
+            # list_illustrations? → figures
+            # ? → abbreviations
+            # ? → edition
+            # cover → ?
+            # cover_front → ?
+            # cover_back → ?
+            # table → ?
+            # manuscript → ?
+            # illustration → ?
+            # section → ?
+            # article → ?
+            # issue → ?
+            # day → ?
+            # month → ?
+            # volume → ?
+            # year → ?
 
     def __add_div(self, insert_node, div, n, tag="div"):
         """

From 15022f59c71c4f42bbca822fe55501ed97eb6768 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 6 Dec 2021 09:02:35 +0100
Subject: [PATCH 15/35] rename changelog

---
 Changelog => CHANGELOG.md | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename Changelog => CHANGELOG.md (100%)

diff --git a/Changelog b/CHANGELOG.md
similarity index 100%
rename from Changelog
rename to CHANGELOG.md

From 553e0fd71ffc4a1d57083496aaa97d929dc4f5c3 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 6 Dec 2021 10:43:27 +0100
Subject: [PATCH 16/35] improve+update changelog

---
 CHANGELOG.md | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 82258e3..54f686d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,31 +8,29 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Changed
 - Added tests for TEI API
 - Added tests for insertion index identification
-- Evaluate texts from all struct types but `binding` and `colour_checker`
 - Add `front`, `body` and `back` per default
+- Log to stderr instead of stdout
 
 ### Fixed
-- https://github.com/slub/mets-mods2tei/issues/43
-- https://github.com/slub/mets-mods2tei/issues/47
+- Evaluate texts from all struct types but `binding` and `colour_checker`, #43
+- Handle errors during language code expansion, and fallback to `Unbekannt`, #47
+- Add ALTO `HYP` text content if available, #52
+- Allow empty logical structMap and structLink, fallback to physical, or empty, #57
+- Allow partial dmdSec (MODS) or amdSec, fallback to empty, #46, #51
 
 ## [0.1.1] - 2020-05-11
 ### Added
-- Treat nested AMD-type (non-logical) divs in logical struct map (i.e.
-newspaper case)
 - Make full text file group selectable by user
-- Allow for file entries (in addition to URLs) in METS
-- Add special treatment for URNs and VD IDs
 - Add poor man's namespace versioning handling
 
 ### Changed
 - Make extraction of subtitles conditional on their presence
-- Use "licence" for all types of licences (even unknown ones)
+- Use "licence" for all types of licences (even unknown ones), #39
 
 ### Fixed
-- https://github.com/slub/mets-mods2tei/issues/28
-- https://github.com/slub/mets-mods2tei/issues/37
-- https://github.com/slub/mets-mods2tei/issues/39
-- https://github.com/slub/mets-mods2tei/issues/41
+- Handle nested `@ADMID="AMD"` divs in logical `structMap` (i.e. newspaper case), #43
+- Allow for local path entries (in addition to URLs) in METS, #41
+- Add special treatment for URNs and VD IDs, #37
 
 ## [0.1.0] - 2019-12-04
 ### Added
@@ -40,13 +38,16 @@ newspaper case)
 - Set `corresp` and `facs` attributes of `pb` elements
 - Store links to `DEFAULT` images in METS
 - Tests for new functionality
+- Add Changelog file, #28
 
 ### Changed
-- Retrieve ALTO files via a dedicated struct link member of the class Mets
-- Move text retrieval to Alto class
+- Retrieve ALTO files via a dedicated struct link member of the class `Mets`
+- Move text retrieval to `Alto` class
 
 ### Removed
 - Get rid of code artifacts carried over from `tocrify`
 
-### Fixed
-- https://github.com/slub/mets-mods2tei/issues/28
+<!-- link-labels -->
+[unreleased]: ../../compare/v0.1.1...master
+[0.1.1]: ../../compare/v0.1.0...v0.1.1
+[0.1.0]: ../../compare/v1.0...v0.1.0

From 27dffe80430b932208d02933f3548aae47479d43 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 6 Dec 2021 14:08:09 +0100
Subject: [PATCH 17/35] differentiate image number and page number

---
 mets_mods2tei/api/mets.py | 13 +++++++++++--
 mets_mods2tei/api/tei.py  |  9 ++++++++-
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 18fa66c..2ec1dac 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -54,6 +54,7 @@ def __init__(self):
         self.mods = None
         self.page_map = {}
         self.order_map = {}
+        self.orderlabel_map = {}
         self.img_map = {}
         self.alto_map = {}
         self.struct_links = {}
@@ -324,6 +325,8 @@ def __spur(self):
             self.page_map[div.get_ID()] = div
             if div.get_ORDER():
                 self.order_map[div.get_ID()] = div.get_ORDER()
+            if div.get_ORDERLABEL():
+                self.orderlabel_map[div.get_ID()] = div.get_ORDERLABEL()
             for fptr in div.get_fptr():
                 if fptr.get_FILEID() in fulltext_map:
                     self.alto_map[div.get_ID()] = fulltext_map[fptr.get_FILEID()]
@@ -514,6 +517,12 @@ def get_alto(self, phys_id):
 
     def get_order(self, phys_id):
         """
-        Return the manually set order for a given physical ID
+        Return the logical (manually set) page number for a given physical ID
         """
-        return self.order_map.get(phys_id, "-1")
+        return self.order_map.get(phys_id, "0")
+
+    def get_orderlabel(self, phys_id):
+        """
+        Return the logical (manually set) page label for a given physical ID
+        """
+        return self.orderlabel_map.get(phys_id, "")
diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index a46a7b1..0477aa6 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -639,7 +639,14 @@ def __add_ocr_to_node(self, node, mets):
                 self.alto_map[alto_link] = alto
 
                 pb = etree.SubElement(node, "%spb" % TEI)
-                pb.set("facs", "#f{:04d}".format(int(mets.get_order(struct_link))))
+                try:
+                    pagenum = list(mets.page_map.keys()).index(struct_link)
+                    pb.set("facs", "#f{:04d}".format(pagenum + 1))
+                except ValueError:
+                    self.logger.warning("cannot determine image number for '%s'", struct_link)
+                pagenum = mets.get_orderlabel(struct_link) or mets.get_order(struct_link)
+                if pagenum:
+                    pb.set("n", str(pagenum))
                 pb.set("corresp", mets.get_img(struct_link))
 
                 for text_block in alto.get_text_blocks():

From c39b6c707171979da2e80603803bb0d01a64f8b5 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 6 Dec 2021 14:15:10 +0100
Subject: [PATCH 18/35] allow passing image fileGrp other than DEFAULT

---
 mets_mods2tei/api/mets.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 2ec1dac..77b6dc0 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -59,6 +59,7 @@ def __init__(self):
         self.alto_map = {}
         self.struct_links = {}
         self.fulltext_group_name = 'FULLTEXT'
+        self.image_group_name = 'DEFAULT'
 
         self.title = None
         self.sub_titles = None
@@ -315,7 +316,7 @@ def __spur(self):
 
         # default
         default_map = {}
-        default_group = self.tree.xpath("//mets:fileGrp[@USE='DEFAULT']", namespaces=ns)
+        default_group = self.tree.xpath("//mets:fileGrp[@USE='%s']" % self.image_group_name, namespaces=ns)
         if default_group:
             for entry in default_group[0].xpath("./mets:file", namespaces=ns):
                 default_map[entry.get("ID")] = entry.find("./" + METS + "FLocat").get("%shref" % XLINK)

From 71fd269e2c66dca1504e85e2755b58e97b1aa690 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 6 Dec 2021 23:14:10 +0100
Subject: [PATCH 19/35] add params for image fileGrp and output file, more
 logging

---
 README.md                              | 18 +++++++---
 mets_mods2tei/api/mets.py              | 50 +++++++++++++++-----------
 mets_mods2tei/api/tei.py               | 19 +++++++---
 mets_mods2tei/scripts/mets_mods2tei.py | 22 +++++++++---
 4 files changed, 74 insertions(+), 35 deletions(-)

diff --git a/README.md b/README.md
index 2df14b2..4ac616d 100644
--- a/README.md
+++ b/README.md
@@ -106,11 +106,22 @@ Usage: mm2tei [OPTIONS] METS
 
   METS: File containing or URL pointing to the METS/MODS XML to be converted
 
+  Parse given METS and its meta-data, and convert it to TEI.
+
+  If `--ocr` is given, then also read the ALTO full-text files from the
+  fileGrp in `--text-group`, and convert page contents accordingly (in
+  physical order). Decorate page boundaries with image and page numbers, and
+  reference the corresponding base image files from `--img-group`.
+
+  Output XML to `--output (use '-' for stdout), log to stderr.`
+
 Options:
+  -O, --output FILENAME           File path to write TEI output to
   -o, --ocr                       Serialize OCR into resulting TEI
-  -T, --text-group TEXT           File group which contains the full text
+  -T, --text-group TEXT           File group which contains the full-text
+  -I, --img-group TEXT            File group which contains the images
   -l, --log-level [DEBUG|INFO|WARN|ERROR|OFF]
-  --help                          Show this message and exit.
+  -h, --help                      Show this message and exit.
 ```
 
 It reads METS XML via URL or file argument and prints the resulting TEI,
@@ -118,5 +129,4 @@ including the extracted information from the MODS part of the METS.
 
 Example:
 
-    mm2tei "https://digital.slub-dresden.de/oai/?verb=GetRecord&metadataPrefix=mets&identifier=oai:de:slub-dresden:db:id-453779263" > tei.xml
-
+    mm2tei -O tei.xml "https://digital.slub-dresden.de/oai/?verb=GetRecord&metadataPrefix=mets&identifier=oai:de:slub-dresden:db:id-453779263"
diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 77b6dc0..955bf5f 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -227,16 +227,16 @@ def __spur(self):
         if amdsec and amdsec[0].get_rightsMD():
             dv = etree.fromstring(amdsec[0].get_rightsMD()[0].get_mdWrap().get_xmlData().get_anytypeobjs_()[0])
         else:
-            dv = []
+            dv = None
 
         # owner of the digital edition
-        self.owner_digital = dv.xpath("//dv:owner", namespaces=ns)[0].text if dv else ""
+        self.owner_digital = dv.xpath("//dv:owner", namespaces=ns)[0].text if dv is not None else ""
 
         # availability/license
         # common case
         self.license = ""
         self.license_url = ""
-        license_nodes = dv.xpath("//dv:license", namespaces=ns) if dv else []
+        license_nodes = dv.xpath("//dv:license", namespaces=ns) if dv is not None else []
         if license_nodes != []:
             self.license = license_nodes[0].text
             self.license_url = ""
@@ -312,35 +312,43 @@ def __spur(self):
         if fulltext_group:
             fulltext_map = {}
             for entry in fulltext_group[0].xpath("./mets:file", namespaces=ns):
-                fulltext_map[entry.get("ID")] = entry.find("./" + METS + "FLocat").get("%shref" % XLINK)
-
-        # default
-        default_map = {}
-        default_group = self.tree.xpath("//mets:fileGrp[@USE='%s']" % self.image_group_name, namespaces=ns)
-        if default_group:
-            for entry in default_group[0].xpath("./mets:file", namespaces=ns):
-                default_map[entry.get("ID")] = entry.find("./" + METS + "FLocat").get("%shref" % XLINK)
+                url = entry.find("./" + METS + "FLocat").get("%shref" % XLINK)
+                self.logger.debug("Found full-text file: %s", url)
+                fulltext_map[entry.get("ID")] = url
+
+        # image
+        image_map = {}
+        image_group = self.tree.xpath("//mets:fileGrp[@USE='%s']" % self.image_group_name, namespaces=ns)
+        if image_group:
+            for entry in image_group[0].xpath("./mets:file", namespaces=ns):
+                url = entry.find("./" + METS + "FLocat").get("%shref" % XLINK)
+                self.logger.debug("Found image file: %s", url)
+                image_map[entry.get("ID")] = url
 
         # struct map physical
         for div in self.get_page_structure().get_div():
-            self.page_map[div.get_ID()] = div
+            page = div.get_ID()
+            self.logger.debug("Found physical page: %s", page)
+            self.page_map[page] = div
             if div.get_ORDER():
-                self.order_map[div.get_ID()] = div.get_ORDER()
+                self.order_map[page] = div.get_ORDER()
             if div.get_ORDERLABEL():
-                self.orderlabel_map[div.get_ID()] = div.get_ORDERLABEL()
+                self.orderlabel_map[page] = div.get_ORDERLABEL()
             for fptr in div.get_fptr():
                 if fptr.get_FILEID() in fulltext_map:
-                    self.alto_map[div.get_ID()] = fulltext_map[fptr.get_FILEID()]
-                elif fptr.get_FILEID() in default_map:
-                    self.img_map[div.get_ID()] = default_map[fptr.get_FILEID()]
+                    self.alto_map[page] = fulltext_map[fptr.get_FILEID()]
+                elif fptr.get_FILEID() in image_map:
+                    self.img_map[page] = image_map[fptr.get_FILEID()]
 
         # struct links
         structlinks = self.tree.xpath("//mets:structLink/*", namespaces=ns)
         for sm_link in structlinks:
-            if sm_link.get("%sto" % XLINK) in self.alto_map:
-                if sm_link.get("%sfrom" % XLINK) not in self.struct_links:
-                    self.struct_links[sm_link.get("%sfrom" % XLINK)] = []
-                self.struct_links[sm_link.get("%sfrom" % XLINK)].append(sm_link.get("%sto" % XLINK))
+            logical = sm_link.get("%sfrom" % XLINK)
+            physical = sm_link.get("%sto" % XLINK)
+            if physical in self.alto_map:
+                self.logger.debug("Found structLink from %s to physical page: %s", logical, physical)
+                pages = self.struct_links.setdefault(logical, list())
+                pages.append(physical)
 
     @property
     def fulltext_group_name(self):
diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index 0477aa6..cf1193a 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -134,7 +134,7 @@ def fill_from_mets(self, mets, ocr=True):
         # div structure
         div = mets.get_div_structure()
         if div is not None:
-            self.logger.info("Found logical structMap for %s", div.get_TYPE())
+            self.logger.debug("Found logical structMap for %s", div.get_TYPE())
             self.add_div_structure(div)
         elif any(mets.alto_map):
             self.logger.warning("Found no logical structMap div, falling back to physical")
@@ -604,13 +604,15 @@ def __add_ocr_to_node(self, node, mets):
         """
         Add text to a given node and recursively add text to children too (post order!)
         """
-        
+
+        node_id = node.get("id")
+        self.logger.debug("Adding text for %s", node_id)
         for childnode in node.iterchildren():
             self.__add_ocr_to_node(childnode, mets)
-        struct_links = mets.get_struct_links(node.get("id"))
-        if not struct_links and node.get("id") in mets.page_map:
+        struct_links = mets.get_struct_links(node_id)
+        if not struct_links and node_id in mets.page_map:
             # already physical
-            struct_links = [node.get("id")]
+            struct_links = [node_id]
         
         # a header will always be on the first page of a div
         first = True
@@ -712,14 +714,18 @@ def add_div_structure(self, div, pages=None):
 
         if pages:
             for page in pages:
+                self.logger.debug("Found physical page %s", page.get_ID())
                 self.__add_div(body, page, 1)
             return
 
         # descend to the deepest AMD
         while div.get_ADMID() is None:
+            self.logger.debug("Found logical outer div type %s: %s", div.get_TYPE(), div.get_ID())
             div = div.get_div()[0]
         start_div = div.get_div()[0]
+        self.logger.debug("Found logical inner div type %s: %s", start_div.get_TYPE(), start_div.get_ID())
         while start_div.get_div() and start_div.get_div()[0].get_ADMID() is not None:
+            self.logger.debug("Found logical inner div type %s: %s", start_div.get_TYPE(), start_div.get_ID())
             div = start_div
             start_div = start_div.get_div()[0]
         
@@ -785,6 +791,9 @@ def __add_div(self, insert_node, div, n, tag="div"):
             #head = etree.SubElement(new_div, "%s%s" % (TEI, "head"))
             #head.text = div.get_LABEL()
             new_div.set("rend", div.get_LABEL())
+        self.logger.debug("Adding %s[@id=%s,@n=%d,@rend=%s] for %s",
+                          tag, div.get_ID(), n, div.get_LABEL() or "",
+                          insert_node.tag.split('}')[-1])
         for sub_div in div.get_div():
             self.__add_div(new_div, sub_div, n+1)
 
diff --git a/mets_mods2tei/scripts/mets_mods2tei.py b/mets_mods2tei/scripts/mets_mods2tei.py
index 35e4b1e..cb4b059 100644
--- a/mets_mods2tei/scripts/mets_mods2tei.py
+++ b/mets_mods2tei/scripts/mets_mods2tei.py
@@ -10,13 +10,24 @@
 from mets_mods2tei import Mets
 from mets_mods2tei import Tei
 
-@click.command()
+@click.command(context_settings={'help_option_names': ['-h', '--help']})
 @click.argument('mets', required=True)
+@click.option('-O', '--output', default="-", type=click.File("wb"), help="File path to write TEI output to")
 @click.option('-o', '--ocr', is_flag=True, default=False, help="Serialize OCR into resulting TEI")
-@click.option('-T', '--text-group', default="FULLTEXT", help="File group which contains the full text")
+@click.option('-T', '--text-group', default="FULLTEXT", help="File group which contains the full-text")
+@click.option('-I', '--img-group', default="DEFAULT", help="File group which contains the images")
 @click.option('-l', '--log-level', type=click.Choice(['DEBUG', 'INFO', 'WARN', 'ERROR', 'OFF']), default='WARN')
-def cli(mets, ocr, text_group, log_level):
-    """ METS: File containing or URL pointing to the METS/MODS XML to be converted """
+def cli(mets, output, ocr, text_group, img_group, log_level):
+    """METS: File containing or URL pointing to the METS/MODS XML to be converted
+
+    Parse given METS and its meta-data, and convert it to TEI.
+
+    If `--ocr` is given, then also read the ALTO full-text files from the fileGrp in `--text-group`,
+    and convert page contents accordingly (in physical order). Decorate page boundaries with image
+    and page numbers, and reference the corresponding base image files from `--img-group`.
+
+    Output XML to `--output (use '-' for stdout), log to stderr.`
+    """
 
     #
     # logging level
@@ -33,6 +44,7 @@ def cli(mets, ocr, text_group, log_level):
     # read in METS
     mets = Mets()
     mets.fulltext_group_name = text_group
+    mets.image_group_name = img_group
     mets.fromfile(f)
 
     #
@@ -41,7 +53,7 @@ def cli(mets, ocr, text_group, log_level):
 
     tei.fill_from_mets(mets, ocr)
 
-    click.echo(tei.tostring())
+    output.write(tei.tostring())
 
 
 if __name__ == '__main__':

From 5c20f9051ae439a57a20ad6bb55f27cafe15308f Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 6 Dec 2021 23:28:06 +0100
Subject: [PATCH 20/35] update changelog

---
 CHANGELOG.md | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 54f686d..7372172 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,11 +5,17 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
+### Added
+- tests for TEI API
+- tests for insertion index identification
+- more logging
+- CLI param for output file
+- CLI param for image fileGrp
+
 ### Changed
-- Added tests for TEI API
-- Added tests for insertion index identification
 - Add `front`, `body` and `back` per default
 - Log to stderr instead of stdout
+- Differentiate between (physical) image nr and (logical) page nr
 
 ### Fixed
 - Evaluate texts from all struct types but `binding` and `colour_checker`, #43

From ad261ff1580e7170d6ab3bd73879fb404dfd136c Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sun, 12 Dec 2021 23:31:17 +0100
Subject: [PATCH 21/35] generalize passing URN and VD ID to all identifiers

---
 mets_mods2tei/api/mets.py | 26 ++++++++------------------
 mets_mods2tei/api/tei.py  | 36 +++++++++---------------------------
 2 files changed, 17 insertions(+), 45 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 955bf5f..85832e9 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -77,8 +77,7 @@ def __init__(self):
         self.encoding_desc = None
         self.owner_manuscript = None
         self.shelf_locators = None
-        self.urn = None
-        self.vd_id = None
+        self.identifiers = None
         self.scripts = None
         self.collections = None
         self.languages = None
@@ -285,14 +284,11 @@ def __spur(self):
 
         #
         # URN and VD ID
-        self.urn = ""
-        self.vd_id = ""
+        self.identifiers = dict()
         identifiers = self.mods.get_identifier()
-        for identifier in identifiers:
-            if identifier.get_type().lower() == "urn":
-                self.urn = identifier.get_valueOf_()
-            elif identifier.get_type().lower().startswith("vd"):
-                self.vd_id = identifier.get_valueOf_()
+        if len(identifiers):
+            for identifier in identifiers:
+                self.identifiers[identifier.get_type()] = identifier.get_valueOf_()
 
         #
         # collections (from relatedItem)
@@ -458,17 +454,11 @@ def get_shelf_locators(self):
         """
         return self.shelf_locators
 
-    def get_urn(self):
+    def get_identifiers(self):
         """
-        Return the URN of the digital representation
+        Return the (dict of) identifiers of the digital representation
         """
-        return self.urn
-
-    def get_vd_id(self):
-        """
-        Return the VD ID of the digital representation
-        """
-        return self.vd_id
+        return self.identifiers
 
     def get_scripts(self):
         """
diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index cf1193a..f8c4de4 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -100,13 +100,12 @@ def fill_from_mets(self, mets, ocr=True):
 
         # shelf locator
         for shelf_locator in mets.get_shelf_locators():
-            self.add_shelfmark(shelf_locator)
+            self.add_ms_identifier("shelfmark", shelf_locator)
 
         # identifiers
-        if mets.get_urn():
-            self.add_urn(mets.get_urn())
-        if mets.get_vd_id():
-            self.add_vd_id(mets.get_vd_id())
+        if mets.get_identifiers():
+            for type_, value in mets.get_identifiers().items():
+                self.add_ms_identifier(type_.upper(), value)
 
         # type description
         if mets.get_scripts():
@@ -493,32 +492,15 @@ def add_repository(self, repository):
         repository_node = etree.SubElement(ms_ident, "%srepository" % TEI)
         repository_node.text = repository
 
-    def add_shelfmark(self, shelfmark):
+    def add_ms_identifier(self, type_, value):
         """
-        Add the shelf mark of the (original) manuscript
+        Add the URN, PURL, VD ID, shelfmark etc. of the digital edition
         """
         ms_ident_idno = self.tree.xpath('//tei:msDesc/tei:msIdentifier/tei:idno', namespaces=ns)[0]
+        # FIXME: URN, DTAID, ... should go to /tei:fileDesc/tei:publicationStmt/tei:idno instead
         idno = etree.SubElement(ms_ident_idno, "%sidno" % TEI)
-        idno.set("type", "shelfmark")
-        idno.text = shelfmark
-
-    def add_urn(self, urn):
-        """
-        Add the URN of the digital edition
-        """
-        ms_ident_idno = self.tree.xpath('//tei:msDesc/tei:msIdentifier/tei:idno', namespaces=ns)[0]
-        idno = etree.SubElement(ms_ident_idno, "%sidno" % TEI)
-        idno.set("type", "URN")
-        idno.text = urn
-
-    def add_vd_id(self, vd_id):
-        """
-        Add the VD ID of the digital edition
-        """
-        ms_ident_idno = self.tree.xpath('//tei:msDesc/tei:msIdentifier/tei:idno', namespaces=ns)[0]
-        idno = etree.SubElement(ms_ident_idno, "%sidno" % TEI)
-        idno.set("type", "VD")
-        idno.text = vd_id
+        idno.set("type", type_)
+        idno.text = value
 
     def set_type_desc(self, description):
         """

From 93fb68469356779ba73d08c05dc6572542e61372 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 13 Dec 2021 13:19:50 +0100
Subject: [PATCH 22/35] =?UTF-8?q?improve=20level,=20title=20and=20idno=20m?=
 =?UTF-8?q?etadata=E2=80=A6?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- for `sourceDesc/biblFull/titleStmt/title/@level`, only use allowed values
  (m/a/j/s/u), and try mapping from top-level logical `div/@TYPE`
- for `sourceDesc/bibl/@type`, try mapping from top-level logical `div/@TYPE`
- instead of ignoring `titleInfo` main and part/volume titles,
  - prefer main title from titleInfo over top-level logical `div/@LABEL`
  - prefer `titleInfo/@type=uniform` or empty over abbrev/alternative/translated
  - also parse and add `partNumber/partName` or `part`
- instead of spilling titleInfo between `fileDesc/titleStmt` and `biblFull/titleStmt`,
  copy the former to the latter when complete, and then add `@level` etc
---
 CHANGELOG.md                        |   5 ++
 mets_mods2tei/api/mets.py           |  85 ++++++++++++++++++--
 mets_mods2tei/api/tei.py            | 120 ++++++++++++++++++++--------
 mets_mods2tei/data/tei_skeleton.xml |   5 +-
 tests/test_mets.py                  |   6 +-
 tests/test_tei.py                   |  19 ++---
 6 files changed, 184 insertions(+), 56 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7372172..69ae629 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -23,6 +23,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Add ALTO `HYP` text content if available, #52
 - Allow empty logical structMap and structLink, fallback to physical, or empty, #57
 - Allow partial dmdSec (MODS) or amdSec, fallback to empty, #46, #51
+- Pass all `mods:identifier`s to `msIdentifier/idno` (not just VD and URN)
+- Parse full `titleInfo` (main/sub/part/volume), and re-use in `biblFull`
+- Prefer `titleInfo/title` over `div/@LABEL` if available
+- Map top logical `div/@TYPE` into allowed `biblFull/title/@level` only
+- Map top logical `div/@TYPE` into appropriate `bibl/@type` if possible
 
 ## [0.1.1] - 2020-05-11
 ### Added
diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 85832e9..7567bc3 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -63,6 +63,8 @@ def __init__(self):
 
         self.title = None
         self.sub_titles = None
+        self.part_titles = None
+        self.volume_titles = None
         self.authors = None
         self.editors = None
         self.places = None
@@ -124,17 +126,74 @@ def __spur(self):
         """
 
         #
-        # main title and manuscript type
+        # get publication level
+        # get main and sub title from top-level logical div as a fallback
+        self.title = ""
+        self.biblevel = None
+        self.bibtype = None
         div = self.get_div_structure()
-        self.title = div.get_LABEL() if div else ""
-        self.type = div.get_TYPE() if div else ""
+        if div:
+            self.title = div.get_LABEL() # overridden by any titleInfo
+            div_type = div.get_TYPE()
+            # differentiate between analytic and closed, periodic and singular, dependent and indepenent types
+            # (for use in bibl/@type and biblFull//title/@level):
+            # FIXME: verify this ruleset is correct/standardized (but criteria do not look orthogonal, e.g. "issue" and "proceeding")
+            if div_type in ["bachelor_thesis", "diploma_thesis", "magister_thesis", "master_thesis", "doctoral_thesis", "habilitation_thesis", "file", "register", "research_paper", "report", "atlas", "album", "letter", "document", "leaflet", "manuscript", "poster", "plan", "study", "judgement", "preprint", "dossier", "paper"]:
+                self.biblevel = 'u' # unpublished
+                self.bibtype = 'M' # monograph
+            elif div_type in ["contained_work", "folder", ]:
+                self.biblevel = 'a'
+                self.bibtype = 'DM' # dependent part of monograph
+                # ? or 'DS' # dependent part of series
+            elif div_type in ["article"]:
+                self.biblevel = 'a' # analytic
+                self.bibtype = 'JA' # journal article
+            elif div_type in ["periodical", "newspaper"]:
+                self.biblevel = 'j' # journal
+                self.bibtype = 'J' # journal
+            elif div_type in ["lecture"]:
+                self.biblevel = 's' # series
+                self.bibtype = '' # ?
+            elif div_type in ["monograph", ]:
+                self.biblevel = 'm' # monograph
+                self.bibtype = 'M' # monograph
+            elif div_type in ["multivolume_work", "volume"]:
+                self.biblevel = 'm' # monograph
+                self.bibtype = 'MM' # monograph within multi-volume monograph
+                # ? or 'MS' # monograph within series
+                # ? or 'MMS' # monograph within multi-volume monograph series
 
         #
-        # sub titles
-        self.sub_titles = []
-        for title_info in self.mods.get_titleInfo():
+        # titleInfo (main, sub, part/volume)
+        self.sub_titles = [] # subtitle (mods:titleInfo[mods:subTitle]
+        self.part_titles = dict() # part title of multipart subseries (mods:titleInfo[mods:partNumber|mods:partName])
+        self.volume_titles = dict() # volume title in multivolume monograph (mods:part[mods:detail])
+        title_infos = self.mods.get_titleInfo()
+        if len(title_infos):
+            def norm_title_first(titleInfo):
+                if not titleInfo.get_type() or titleInfo.get_type() == 'simple':
+                    # prefer untyped entry ('simple' most likely is from generateDS)
+                    return -1
+                if titleInfo.get_type() == 'uniform':
+                    return 0
+                return 1
+            title_info = sorted(title_infos, key=norm_title_first)[0]
+            if title_info.get_title():
+                self.title = title_info.get_title()[0].get_valueOf_().strip()
             for sub_title in title_info.get_subTitle():
                 self.sub_titles.append(sub_title.get_valueOf_().strip())
+            for part_number, part_name in zip(title_info.get_partNumber(), title_info.get_partName()):
+                self.part_titles[part_number.get_valueOf_().strip()] = part_name.get_valueOf_().strip()
+        part_infos = self.mods.get_part()
+        if len(part_infos):
+            part_info = part_infos[0]
+            order = str(part_info.get_order() or 0)
+            for detail in part_info.get_detail():
+                typ = detail.get_type()
+                val = ', '.join([title.get_valueOf_().strip()
+                                 for title in detail.get_number() + detail.get_caption() + detail.get_title()])
+                self.volume_titles[order, typ] = val
+
         #
         # authors and editors
         self.authors = []
@@ -366,10 +425,22 @@ def get_main_title(self):
 
     def get_sub_titles(self):
         """
-        Return the main title of the work.
+        Return the sub-titles of the work.
         """
         return self.sub_titles
 
+    def get_part_titles(self):
+        """
+        Return the part titles of the work.
+        """
+        return self.part_titles
+
+    def get_volume_titles(self):
+        """
+        Return the volume titles of the work.
+        """
+        return self.volume_titles
+
     def get_authors(self):
         """
         Return the author of the work.
diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index f8c4de4..04bef62 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -38,6 +38,7 @@ def tostring(self):
         """
         Serializes the TEI object as xml string.
         """
+        # needs lxml>=4.5: etree.indent(self.tree, space="  ")
         return etree.tostring(self.tree, encoding="utf-8")
 
     def fill_from_mets(self, mets, ocr=True):
@@ -50,13 +51,16 @@ def fill_from_mets(self, mets, ocr=True):
 
         # main title
         self.set_main_title(mets.get_main_title())
+        for sub in mets.get_sub_titles():
+            self.add_sub_title(sub)
+        for number, part in mets.get_part_titles().items():
+            self.add_part_title(number, part)
+        for (order, typ), volume in mets.get_volume_titles().items():
+            self.add_volume_title(order, typ, volume)
+        self.init_biblFull()
 
         # publication level
-        self.set_publication_level(mets.type)
-
-        # sub titles
-        for sub_title in mets.get_sub_titles():
-            self.add_sub_title(sub_title)
+        self.set_publication_level(mets.biblevel)
 
         # authors
         for typ, author in mets.get_authors():
@@ -100,12 +104,14 @@ def fill_from_mets(self, mets, ocr=True):
 
         # shelf locator
         for shelf_locator in mets.get_shelf_locators():
-            self.add_ms_identifier("shelfmark", shelf_locator)
+            self.add_identifier("shelfmark", shelf_locator)
 
         # identifiers
         if mets.get_identifiers():
             for type_, value in mets.get_identifiers().items():
-                self.add_ms_identifier(type_.upper(), value)
+                if type_ in ["vd16", "vd17", "vd18"]:
+                    type_ = "VD"
+                self.add_identifier(type_.upper(), value)
 
         # type description
         if mets.get_scripts():
@@ -125,7 +131,7 @@ def fill_from_mets(self, mets, ocr=True):
 
         #
         # citation
-        self.compile_bibl()
+        self.compile_bibl(mets.bibtype)
 
         #
         # text part
@@ -156,13 +162,6 @@ def main_title(self):
         """
         return self.tree.xpath('//tei:titleStmt/tei:title[@type="main"]', namespaces=ns)[0].text
     
-    @property
-    def publication_level(self):
-        """
-        Return the level of publication ('monographic' vs. 'analytic')
-        """
-        return self.tree.xpath('//tei:sourceDesc/tei:biblFull/tei:titleStmt/tei:title[@type="main"]', namespaces=ns)[0].get("level")
-
     @property
     def subtitles(self):
         """
@@ -182,6 +181,13 @@ def authors(self):
             authors.append(", ".join(author.xpath('descendant-or-self::*/text()')))
         return authors
 
+    @property
+    def publication_level(self):
+        """
+        Return the level of publication ('monographic' vs. 'analytic')
+        """
+        return self.tree.xpath('//tei:sourceDesc/tei:biblFull/tei:titleStmt/tei:title[@type="main"]', namespaces=ns)[0].get("level")
+
     @property
     def dates(self):
         """
@@ -330,26 +336,70 @@ def bibl(self):
 
     def set_main_title(self, string):
         """
-        Set the main title of the title statements.
+        Set the main title of the tei:titleStmt.
         """
-        for main_title in self.tree.xpath('//tei:titleStmt/tei:title[@type="main"]', namespaces=ns):
-            main_title.text = string
+        titleStmt = self.tree.xpath('//tei:titleStmt', namespaces=ns)[0]
+        for node in titleStmt.xpath('tei:title[@type="main"]', namespaces=ns):
+            node.text = string
 
-    def set_publication_level(self, level):
+    def add_sub_title(self, string):
         """
-        Set the level of publication ('monographic' vs. 'analytic')
+        Add a sub-title of the tei:titleStmt.
         """
-        self.tree.xpath('//tei:sourceDesc/tei:biblFull/tei:titleStmt/tei:title[@type="main"]', namespaces=ns)[0].set("level", level)
+        titleStmt = self.tree.xpath('//tei:titleStmt', namespaces=ns)[0]
+        node = etree.Element("%stitle" % TEI)
+        node.set("type", "sub")
+        node.text = string
+        titleStmt.append(copy.deepcopy(node))
 
-    def add_sub_title(self, string):
+    def add_part_title(self, number, string):
         """
-        Add a sub title to the title statements.
+        Add a part title of the tei:titleStmt.
         """
-        sub_title = etree.Element("%stitle" % TEI)
-        sub_title.set("type", "sub")
-        sub_title.text = string
-        for title_stmt in self.tree.xpath('//tei:titleStmt', namespaces=ns):
-            title_stmt.append(copy.deepcopy(sub_title))
+        titleStmt = self.tree.xpath('//tei:titleStmt', namespaces=ns)[0]
+        node = etree.Element("%stitle" % TEI)
+        node.set("type", "part")
+        node.set("n", number)
+        node.text = string
+        titleStmt.append(copy.deepcopy(node))
+
+    def add_volume_title(self, number, typ, string):
+        """
+        Add a volume title of the tei:titleStmt.
+        """
+        titleStmt = self.tree.xpath('//tei:titleStmt', namespaces=ns)[0]
+        node = etree.Element("%stitle" % TEI)
+        node.set("type", typ)
+        node.set("n", number)
+        node.text = string
+        titleStmt.append(copy.deepcopy(node))
+
+    def init_biblFull(self):
+        """
+        Set the main, sub, and part/volume titles of the tei:biblFull by copying from tei:titleStmt.
+        """
+        titleStmt = self.tree.xpath('//tei:titleStmt', namespaces=ns)[0]
+        bibl = self.tree.xpath('//tei:sourceDesc/tei:biblFull', namespaces=ns)[0]
+        bibl.append(copy.deepcopy(titleStmt))
+
+    def set_publication_level(self, level):
+        """
+        Set the level of publication:
+        - 'm': (monographic) the title applies to a monograph such as a book
+               or other item considered to be a distinct publication, 
+               including single volumes of multi-volume works
+        - 'a': (analytic) the title applies to an analytic item, such as an article, 
+               poem, or other work published as part of a larger item.
+        - 'j': (journal) the title applies to any serial or periodical publication
+               such as a journal, magazine, or newspaper
+        - 's': (series) the title applies to a series of otherwise distinct publications
+               such as a collection
+        - 'u': (unpublished) the title applies to any unpublished material
+               (including theses and dissertations unless published by a commercial press)
+        """
+        assert level in ['m', 'a', 'j', 's', 'u']
+        for title in self.tree.xpath('//tei:sourceDesc/tei:biblFull/tei:titleStmt/tei:title', namespaces=ns):
+            title.set("level", level)
 
     def add_author(self, person, typ):
         """
@@ -492,13 +542,13 @@ def add_repository(self, repository):
         repository_node = etree.SubElement(ms_ident, "%srepository" % TEI)
         repository_node.text = repository
 
-    def add_ms_identifier(self, type_, value):
+    def add_identifier(self, type_, value):
         """
         Add the URN, PURL, VD ID, shelfmark etc. of the digital edition
         """
-        ms_ident_idno = self.tree.xpath('//tei:msDesc/tei:msIdentifier/tei:idno', namespaces=ns)[0]
+        ms_ident = self.tree.xpath('//tei:msDesc/tei:msIdentifier/tei:idno', namespaces=ns)[0]
         # FIXME: URN, DTAID, ... should go to /tei:fileDesc/tei:publicationStmt/tei:idno instead
-        idno = etree.SubElement(ms_ident_idno, "%sidno" % TEI)
+        idno = etree.SubElement(ms_ident, "%sidno" % TEI)
         idno.set("type", type_)
         idno.text = value
 
@@ -542,16 +592,16 @@ def add_collection(self, collection):
         creation = etree.SubElement(profile_desc, "%screation" % TEI)
         creation.text = collection
 
-    def compile_bibl(self):
+    def compile_bibl(self, type_):
         """
         Compile the content of the short citation element 'bibl' based on the current state
         """
-        if self.publication_level:
-            self.bibl.set("type", self.publication_level)
+        if type_:
+            self.bibl.set("type", type_)
         bibl_text = ""
         if self.authors:
             bibl_text += "; ".join(self.authors) + ": "
-        elif self.publication_level == "monograph":
+        elif type_.startswith("M"):
             bibl_text = "[N. N.], "
         bibl_text += self.main_title + "."
         if self.places:
diff --git a/mets_mods2tei/data/tei_skeleton.xml b/mets_mods2tei/data/tei_skeleton.xml
index 1e04da9..142e491 100644
--- a/mets_mods2tei/data/tei_skeleton.xml
+++ b/mets_mods2tei/data/tei_skeleton.xml
@@ -8,13 +8,12 @@
         <title type="main">[Haupttitel]</title>
       </titleStmt>
       <publicationStmt>
+        <idno>
+        </idno>
       </publicationStmt>
       <sourceDesc>
         <bibl type="M">[Zitiertitel]</bibl>
         <biblFull>
-          <titleStmt>
-            <title level="m" type="main">[Haupttitel einer Monographie]</title>
-          </titleStmt>
           <publicationStmt>
           </publicationStmt>
         </biblFull>
diff --git a/tests/test_mets.py b/tests/test_mets.py
index bf71438..984847e 100644
--- a/tests/test_mets.py
+++ b/tests/test_mets.py
@@ -136,7 +136,9 @@ def test_data_assignment(subtests, datadir):
         assert(mets.get_shelf_locators() == ['Hist.Amer.1497'])
 
     with subtests.test("Check URN"):
-        assert(mets.get_urn() == 'urn:nbn:de:bsz:14-db-id4971666239')
+        assert "urn" in mets.get_identifiers()
+        assert mets.get_identifiers()["urn"] == 'urn:nbn:de:bsz:14-db-id4971666239'
 
     with subtests.test("Check VD ID"):
-        assert(mets.get_vd_id() == 'VD18 11413883')
+        assert "vd18" in mets.get_identifiers()
+        assert mets.get_identifiers()["vd18"] == 'VD18 11413883'
diff --git a/tests/test_tei.py b/tests/test_tei.py
index 575c2c6..f6655ca 100644
--- a/tests/test_tei.py
+++ b/tests/test_tei.py
@@ -59,10 +59,6 @@ def test_data_assignment(subtests):
         tei.set_main_title("Testbuch")
         assert(tei.main_title == "Testbuch")
 
-    with subtests.test("Check publication level"):
-        tei.set_publication_level("m")
-        assert(tei.publication_level == "m")
-
     with subtests.test("Check first subtitle"):
         tei.add_sub_title("Untertitel 1")
         assert(tei.subtitles == ["Untertitel 1"])
@@ -71,6 +67,11 @@ def test_data_assignment(subtests):
         tei.add_sub_title("Untertitel 2")
         assert(tei.subtitles == ["Untertitel 1", "Untertitel 2"])
 
+    with subtests.test("Check publication level"):
+        tei.init_biblFull()
+        tei.set_publication_level("m")
+        assert(tei.publication_level == "m")
+
     with subtests.test("Check first author"):
         tei.add_author({'family': 'Mustermann', 'given': 'Max', 'date': '12.10.1956', 'title': 'Dr.'}, "personal")
         assert(tei.authors == ["Mustermann, Max, Dr."])
@@ -133,16 +134,16 @@ def test_data_assignment(subtests):
         assert(tei.repositories == ["Kitodo.Production", "Saxonica"])
 
     with subtests.test("Check shelfmarks"):
-        tei.add_shelfmark("Foo 25")
-        tei.add_shelfmark("HAL 9000")
+        tei.add_identifier("shelfmark", "Foo 25")
+        tei.add_identifier("shelfmark", "HAL 9000")
         assert(tei.shelfmarks == ["Foo 25", "HAL 9000"])
 
     with subtests.test("Check VD ID"):
-        tei.add_vd_id("VD18 11413883")
+        tei.add_identifier("VD", "VD18 11413883")
         assert(tei.vd_id == "VD18 11413883")
 
     with subtests.test("Check URN"):
-        tei.add_urn("urn:nbn:de:bsz:14-db-id4971666239")
+        tei.add_identifier("URN", "urn:nbn:de:bsz:14-db-id4971666239")
         assert(tei.urn == "urn:nbn:de:bsz:14-db-id4971666239")
 
     with subtests.test("Check first extent"):
@@ -158,5 +159,5 @@ def test_data_assignment(subtests):
         assert(tei.collections == ["LDP"])
 
     with subtests.test("Check bibl"):
-        tei.compile_bibl()
+        tei.compile_bibl('M')
         assert(tei.bibl.text == "Mustermann, Max, Dr.; Mustermann Max 12.10.1956 Dr.: Testbuch. Dresden u. a., 01.01.1823.")

From 9a5f48627984f19ccc4f0790c37ab3ca66553aae Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 13 Dec 2021 18:12:54 +0100
Subject: [PATCH 23/35] fall back to biblFull title level u

---
 mets_mods2tei/api/tei.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index 04bef62..ba380d5 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -60,7 +60,7 @@ def fill_from_mets(self, mets, ocr=True):
         self.init_biblFull()
 
         # publication level
-        self.set_publication_level(mets.biblevel)
+        self.set_publication_level(mets.biblevel or 'u')
 
         # authors
         for typ, author in mets.get_authors():

From 55353e53f0a92d8c25c4c774e4256fef677c4114 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Tue, 14 Dec 2021 01:16:54 +0100
Subject: [PATCH 24/35] keep going if there is no author and div type

---
 mets_mods2tei/api/tei.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index ba380d5..bc787a8 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -601,7 +601,7 @@ def compile_bibl(self, type_):
         bibl_text = ""
         if self.authors:
             bibl_text += "; ".join(self.authors) + ": "
-        elif type_.startswith("M"):
+        elif type_ and type_.startswith("M"):
             bibl_text = "[N. N.], "
         bibl_text += self.main_title + "."
         if self.places:

From 0bf8bd350395457e2cc5f6b0378f2ae02793be62 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 20 Dec 2021 01:16:42 +0100
Subject: [PATCH 25/35] fix tei:collection

---
 mets_mods2tei/api/tei.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index bc787a8..5a989a4 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -324,7 +324,7 @@ def collections(self):
         Return information on the collections of the work represented
         by the TEI Header.
         """
-        return [collection.text for collection in self.tree.xpath('//tei:profileDesc/tei:creation', namespaces=ns)]
+        return [collection.text for collection in self.tree.xpath('//tei:msDesc/tei:msIdentifier/tei:collection', namespaces=ns)]
 
     @property
     def bibl(self):
@@ -588,9 +588,9 @@ def add_collection(self, collection):
         """
         Add a (free-text) collection of the digital document
         """
-        profile_desc = self.tree.xpath('//tei:profileDesc', namespaces=ns)[0]
-        creation = etree.SubElement(profile_desc, "%screation" % TEI)
-        creation.text = collection
+        profile_desc = self.tree.xpath('//tei:msDesc/tei:msIdentifier', namespaces=ns)[0]
+        coll = etree.SubElement(profile_desc, "%scollection" % TEI)
+        coll.text = collection
 
     def compile_bibl(self, type_):
         """

From 7962b8c5d43a836c96d26df1e104c5e90698859d Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 20 Dec 2021 01:19:27 +0100
Subject: [PATCH 26/35] fix tei:repository (from list-valued
 mods:physicalLocation), add tei:idno from mods:url

---
 mets_mods2tei/api/mets.py | 19 ++++++++++++++-----
 mets_mods2tei/api/tei.py  | 29 ++++++++++++++++++++++++-----
 2 files changed, 38 insertions(+), 10 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 7567bc3..8221bf1 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -77,7 +77,8 @@ def __init__(self):
         self.license_url = None
         self.encoding_date = None
         self.encoding_desc = None
-        self.owner_manuscript = None
+        self.location_phys = None
+        self.location_urls = None
         self.shelf_locators = None
         self.identifiers = None
         self.scripts = None
@@ -339,7 +340,9 @@ def norm_title_first(titleInfo):
             if location.get_shelfLocator():
                 self.shelf_locators.extend([shelf_locator.get_valueOf_() for shelf_locator in location.get_shelfLocator()])
             elif location.get_physicalLocation():
-                self.owner_manuscript = location.get_physicalLocation()
+                self.location_phys = location.get_physicalLocation()[0]
+            elif location.get_url():
+                self.location_urls = location.get_url()
 
         #
         # URN and VD ID
@@ -513,11 +516,17 @@ def get_encoding_description(self):
         """
         return self.encoding_desc
 
-    def get_owner_manuscript(self):
+    def get_location_phys(self):
         """
-        Return the owner of the original manuscript
+        Return the physical location of the original manuscript
         """
-        return self.owner_manuscript
+        return self.location_phys
+
+    def get_location_urls(self):
+        """
+        Return the URL location of the original manuscript
+        """
+        return self.location_urls
 
     def get_shelf_locators(self):
         """
diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index 5a989a4..0a3f65c 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -5,6 +5,7 @@
 import os
 import logging
 import copy
+import re
 
 from contextlib import closing
 from urllib.request import urlopen
@@ -99,8 +100,26 @@ def fill_from_mets(self, mets, ocr=True):
         self.set_encoding_description(mets.get_encoding_description())
 
         # repository
-        if mets.get_owner_manuscript():
-            self.add_repository(mets.get_owner_manuscript())
+        if mets.get_location_phys():
+            # hard to distinguish between settlement, institution and repository at this point
+            self.add_repository(mets.get_location_phys())
+        if mets.get_location_urls():
+            for url in mets.get_location_urls():
+                # hard to determine type of URL at this point – could be (some form of) presentation,
+                # URN, PPN, EPN, DOI, URLWeb, URLCatalogue, URLImages, URLText, URLHTML, URLXML, URLTCF, URLIIIF
+                if url.startswith("urn:"):
+                    typ = "URN"
+                elif re.fullmatch("10[.][0-9]*/.*", url):
+                    typ = "DOI"
+                elif re.fullmatch("[0-9]{8}[0-9X]{1,2}", url):
+                    typ = "PPN"
+                elif re.fullmatch("([0-9]+-)+[0-9]+", url):
+                    typ = "ISBN"
+                elif re.fullmatch("[0-9]{4}-[0-9]{3}[0-9xX]", url):
+                    typ = "ISSN"
+                else:
+                    typ = "URL"
+                self.add_identifier(typ, url)
 
         # shelf locator
         for shelf_locator in mets.get_shelf_locators():
@@ -534,13 +553,13 @@ def set_encoding_description(self, creator):
             encoding_desc_details = etree.SubElement(encoding_desc, "%sp" % TEI)
             encoding_desc_details.text = "Encoded with the help of %s." % creator
 
-    def add_repository(self, repository):
+    def add_repository(self, name):
         """
         Add the repository of the (original) manuscript
         """
         ms_ident = self.tree.xpath('//tei:msDesc/tei:msIdentifier', namespaces=ns)[0]
-        repository_node = etree.SubElement(ms_ident, "%srepository" % TEI)
-        repository_node.text = repository
+        repository = etree.SubElement(ms_ident, "%srepository" % TEI)
+        repository.text = name
 
     def add_identifier(self, type_, value):
         """

From 073f2b1c816c4eb822f20aa81d25e1f611f3b19b Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 20 Dec 2021 01:59:23 +0100
Subject: [PATCH 27/35] fix 7962b8c5

---
 mets_mods2tei/api/mets.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 8221bf1..8126081 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -340,9 +340,9 @@ def norm_title_first(titleInfo):
             if location.get_shelfLocator():
                 self.shelf_locators.extend([shelf_locator.get_valueOf_() for shelf_locator in location.get_shelfLocator()])
             elif location.get_physicalLocation():
-                self.location_phys = location.get_physicalLocation()[0]
+                self.location_phys = location.get_physicalLocation()[0].get_valueOf_()
             elif location.get_url():
-                self.location_urls = location.get_url()
+                self.location_urls = [url.get_valueOf_() for url in location.get_url()]
 
         #
         # URN and VD ID

From 8d2fc4163848e016f7f06f48e1638d19eae7c2a7 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 20 Dec 2021 02:42:56 +0100
Subject: [PATCH 28/35] add tei:notesStmt/tei:note from mods:note

---
 mets_mods2tei/api/mets.py |  9 ++++++++-
 mets_mods2tei/api/tei.py  | 17 +++++++++++++++++
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 8126081..5691910 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -69,6 +69,7 @@ def __init__(self):
         self.editors = None
         self.places = None
         self.dates = None
+        self.notes = None
         self.publishers = None
         self.edition = None
         self.digital_origin = None
@@ -214,6 +215,12 @@ def norm_title_first(titleInfo):
                 elif role.get_valueOf_() == "aut":
                     self.authors.append((typ, person))
 
+        notes = self.mods.get_note()
+        if notes:
+            self.notes = [note.get_valueOf_() for note in notes]
+        else:
+            self.notes = []
+
         #
         # orgin info
         origin_info = self.mods.get_originInfo()
@@ -224,7 +231,7 @@ def norm_title_first(titleInfo):
             for place in origin_info[0].get_place():
                 place_ext = {}
                 for place_term in place.get_placeTerm():
-                    place_ext[place_term.get_type()] = place_term.get_valueOf_()
+                    place_ext[place_term.get_type() or 'text'] = place_term.get_valueOf_()
                 self.places.append(place_ext)
 
         # publication dates
diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index 0a3f65c..b6676cc 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -67,6 +67,10 @@ def fill_from_mets(self, mets, ocr=True):
         for typ, author in mets.get_authors():
             self.add_author(author,typ)
 
+        # notes
+        for note in mets.get_notes():
+            self.add_note(note)
+
         # places
         for place in mets.get_places():
             self.add_place(place)
@@ -445,6 +449,19 @@ def add_author(self, person, typ):
         for title_stmt in self.tree.xpath('//tei:titleStmt', namespaces=ns):
             title_stmt.append(copy.deepcopy(author))
 
+    def add_note(self, note):
+        """
+        Add a note with details about the document.
+        """
+        fileDesc = self.tree.xpath('//tei:fileDesc', namespaces=ns)[0]
+        if not fileDesc.xpath('/tei:notesStmt', namespaces=ns):
+            notes = etree.SubElement(fileDesc, "%snotesStmt" % TEI)
+        else:
+            notes = fileDesc.xpath('/tei:notesStmt', namespaces=ns)[0]
+        node = etree.SubElement(notes, "%snote" % TEI)
+        node.text = note
+        node.set("type", "remarkDocument")
+
     def add_place(self, place):
         """
         Add a publication place to the publication statement.

From 06f1ccfc66a2fb45852e312e44a54ef42982667b Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 20 Dec 2021 04:31:07 +0100
Subject: [PATCH 29/35] fix tei:editionStmt (does not belong under titleStmt)

---
 mets_mods2tei/api/tei.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index b6676cc..a7c893d 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -68,7 +68,7 @@ def fill_from_mets(self, mets, ocr=True):
             self.add_author(author,typ)
 
         # notes
-        for note in mets.get_notes():
+        for note in mets.notes:
             self.add_note(note)
 
         # places
@@ -277,7 +277,7 @@ def digital_editions(self):
         Return information on the editions of the digitalized work represented
         by the TEI Header.
         """
-        return [digital_edition.text for digital_edition in self.tree.xpath('//tei:fileDesc/tei:titleStmt/tei:editionStmt/tei:edition', namespaces=ns)]
+        return [digital_edition.text for digital_edition in self.tree.xpath('//tei:fileDesc/tei:editionStmt/tei:edition', namespaces=ns)]
 
     @property
     def encoding_dates(self):
@@ -509,7 +509,7 @@ def add_digital_edition(self, digital_edition):
         """
         Add an edition statement with details on the digital edition.
         """
-        title_stmt = self.tree.xpath('//tei:titleStmt', namespaces=ns)[0]
+        title_stmt = self.tree.xpath('//tei:fileDesc', namespaces=ns)[0]
         edition_stmt = etree.SubElement(title_stmt, "%seditionStmt" % TEI)
         edition = etree.SubElement(edition_stmt, "%sedition" % TEI)
         edition.text = digital_edition

From c49c2a4e47be1afd946f767892efe3e57833829e Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 20 Dec 2021 04:32:34 +0100
Subject: [PATCH 30/35] add tei:keywords | tei:classCode under tei:textClass
 (for mods:subject | mods:classification)

---
 mets_mods2tei/api/mets.py | 22 ++++++++++++++++++++++
 mets_mods2tei/api/tei.py  | 39 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index 5691910..fe77cab 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -85,6 +85,8 @@ def __init__(self):
         self.scripts = None
         self.collections = None
         self.languages = None
+        self.classifications = None
+        self.subjects = None
         self.extents = None
         self.series = None
 
@@ -272,6 +274,26 @@ def norm_title_first(titleInfo):
         if not self.scripts:
             self.scripts.append(self.script_iso.get('Unknown'))
 
+        #
+        # classifications and subjects
+        classifications = self.mods.get_classification()
+        self.classifications = dict()
+        if classifications:
+            for classification in classifications:
+                codes = self.classifications.setdefault(classification.get_authority(), list())
+                codes.append(classification.get_valueOf_())
+        subjects = self.mods.get_subject()
+        self.subjects = dict()
+        if subjects:
+            for subject in subjects:
+                keywords = self.subjects.setdefault(subject.get_authority(), list())
+                for topic in subject.topic:
+                    keywords.append(('topic', topic.get_valueOf_()))
+                for geographic in subject.geographic:
+                    keywords.append(('geographic', geographic.get_valueOf_()))
+                for temporal in subject.temporal:
+                    keywords.append(('temporal', temporal.get_valueOf_()))
+
         #
         # physical description
         physical_description = self.mods.get_physicalDescription()
diff --git a/mets_mods2tei/api/tei.py b/mets_mods2tei/api/tei.py
index a7c893d..ccdda13 100644
--- a/mets_mods2tei/api/tei.py
+++ b/mets_mods2tei/api/tei.py
@@ -144,6 +144,15 @@ def fill_from_mets(self, mets, ocr=True):
         for ident_name in mets.get_languages().items():
             self.add_language(ident_name)
 
+        # classes
+        for scheme in mets.classifications:
+            classes = mets.classifications[scheme]
+            for code in classes:
+                self.add_classcode(scheme, code)
+        for scheme in mets.subjects:
+            keywords = mets.subjects[scheme]
+            self.add_keywords(scheme, keywords)
+
         # extents
         for extent in mets.extents:
             self.add_extent(extent)
@@ -598,6 +607,36 @@ def set_type_desc(self, description):
             par = etree.SubElement(type_desc, "%sp" % TEI)
             par.text = line
 
+    def add_classcode(self, scheme, code):
+        """
+        Add a document classification code.
+        """
+        profile_desc = self.tree.xpath('//tei:profileDesc', namespaces=ns)[0]
+        if not profile_desc.xpath('/tei:textClass', namespaces=ns):
+            textclass = etree.SubElement(profile_desc, "%stextClass" % TEI)
+        else:
+            textclass = profile_desc.xpath('/tei:textClass', namespaces=ns)[0]
+        classcode = etree.SubElement(textclass, "%sclassCode" % TEI)
+        classcode.set("scheme", scheme)
+        classcode.text = code
+
+    def add_keywords(self, scheme, terms):
+        """
+        Add a document classification list of terms.
+        """
+        profile_desc = self.tree.xpath('//tei:profileDesc', namespaces=ns)[0]
+        if not profile_desc.xpath('/tei:textClass', namespaces=ns):
+            textclass = etree.SubElement(profile_desc, "%stextClass" % TEI)
+        else:
+            textclass = profile_desc.xpath('/tei:textClass', namespaces=ns)[0]
+        keywords = etree.SubElement(textclass, "%skeywords" % TEI)
+        keywords.set("scheme", scheme)
+        for type_, term in terms:
+            node = etree.SubElement(keywords, "%sterm" % TEI)
+            node.text = term
+            if type_:
+                node.set("type", type_)
+
     def add_language(self, language):
         """
         Add a language of the source document

From 27127febd228a73d2da5d3568e4c61f05fdee939 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 20 Dec 2021 10:25:04 +0100
Subject: [PATCH 31/35] chdir to METS dir if not URL

---
 mets_mods2tei/scripts/mets_mods2tei.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mets_mods2tei/scripts/mets_mods2tei.py b/mets_mods2tei/scripts/mets_mods2tei.py
index cb4b059..7d08253 100644
--- a/mets_mods2tei/scripts/mets_mods2tei.py
+++ b/mets_mods2tei/scripts/mets_mods2tei.py
@@ -39,6 +39,8 @@ def cli(mets, output, ocr, text_group, img_group, log_level):
         f = urlopen(mets)
     except:
         f = open(mets, "rb")
+        # physical file: enter METS directory for relative FLocat refs
+        os.chdir(os.path.dirname(mets))
 
     #
     # read in METS

From 8ac0747e086174d12041e52c5e558796f200ebf3 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 20 Dec 2021 10:30:51 +0100
Subject: [PATCH 32/35] fix mods:location (only once, but multiple contents)

---
 mets_mods2tei/api/mets.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mets_mods2tei/api/mets.py b/mets_mods2tei/api/mets.py
index fe77cab..1533bdb 100644
--- a/mets_mods2tei/api/mets.py
+++ b/mets_mods2tei/api/mets.py
@@ -365,12 +365,13 @@ def norm_title_first(titleInfo):
 
         # location-related elements are optional or conditional
         self.shelf_locators = []
-        for location in self.mods.get_location():
+        if self.mods.get_location():
+            location = self.mods.get_location()[0]
             if location.get_shelfLocator():
                 self.shelf_locators.extend([shelf_locator.get_valueOf_() for shelf_locator in location.get_shelfLocator()])
-            elif location.get_physicalLocation():
+            if location.get_physicalLocation():
                 self.location_phys = location.get_physicalLocation()[0].get_valueOf_()
-            elif location.get_url():
+            if location.get_url():
                 self.location_urls = [url.get_valueOf_() for url in location.get_url()]
 
         #

From 20546afbb2b98dccfcf28cf7ecef2050290c1c33 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 20 Dec 2021 10:33:39 +0100
Subject: [PATCH 33/35] fix regression in 27127febd

---
 mets_mods2tei/scripts/mets_mods2tei.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mets_mods2tei/scripts/mets_mods2tei.py b/mets_mods2tei/scripts/mets_mods2tei.py
index 7d08253..da677f1 100644
--- a/mets_mods2tei/scripts/mets_mods2tei.py
+++ b/mets_mods2tei/scripts/mets_mods2tei.py
@@ -40,7 +40,7 @@ def cli(mets, output, ocr, text_group, img_group, log_level):
     except:
         f = open(mets, "rb")
         # physical file: enter METS directory for relative FLocat refs
-        os.chdir(os.path.dirname(mets))
+        os.chdir(os.path.normpath(os.path.dirname(mets)))
 
     #
     # read in METS

From f33a4ca30269e204b35f78ed95256d5eb5681acd Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Thu, 6 Jan 2022 12:46:04 +0100
Subject: [PATCH 34/35] drop Python 3.5

---
 .circleci/config.yml | 2 +-
 setup.py             | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.circleci/config.yml b/.circleci/config.yml
index 668e893..9d95978 100644
--- a/.circleci/config.yml
+++ b/.circleci/config.yml
@@ -45,7 +45,7 @@ workflows:
       - test:
           matrix:
             parameters:
-              version: [3.5.10, 3.6.15, 3.7.12, 3.8.12, 3.9.9]
+              version: [3.6.15, 3.7.12, 3.8.12, 3.9.9]
   deploy:
     jobs:
       - pypi:
diff --git a/setup.py b/setup.py
index 4e368e1..9374c1b 100644
--- a/setup.py
+++ b/setup.py
@@ -14,7 +14,7 @@
     packages=find_packages(exclude=('tests', 'docs')),
     package_data={'mets_mods2tei' : ['data/tei_skeleton.xml', 'data/iso15924-utf8-20180827.txt']},
     install_requires=open('requirements.txt').read().split('\n'),
-    python_requires=">=3.5",
+    python_requires=">=3.6",
     classifiers=[
         'Development Status :: 5 - Production/Stable',
         'Environment :: Console',

From 8204bfc04dc6dd39f71af62a5772b5f73b20f4ad Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kay-Michael=20W=C3=BCrzner?= <wuerzner@gmail.com>
Date: Thu, 6 Jan 2022 13:58:30 +0100
Subject: [PATCH 35/35] Revert regression fix in README.md

https://www.capstoneediting.com.au/blog/how-to-hyphenate-a-compound-noun
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 4ac616d..0f9ce70 100644
--- a/README.md
+++ b/README.md
@@ -118,7 +118,7 @@ Usage: mm2tei [OPTIONS] METS
 Options:
   -O, --output FILENAME           File path to write TEI output to
   -o, --ocr                       Serialize OCR into resulting TEI
-  -T, --text-group TEXT           File group which contains the full-text
+  -T, --text-group TEXT           File group which contains the full text
   -I, --img-group TEXT            File group which contains the images
   -l, --log-level [DEBUG|INFO|WARN|ERROR|OFF]
   -h, --help                      Show this message and exit.