Merge branch 'master' into mvp2

ePICreator/pdf-to-html/test-pdf-to-html-en.py

@@ -0,0 +1,78 @@
+import fitz  # PyMuPDF
+import re
+
+
+# Define the path to the PDF file
+pdf_path = "../source-data/epi/pil.10637.pdf"
+html_file_path = "./pil.10637.md"
+
+
+# Open the PDF file
+def replace_unicode_character(input_string, character_to_replace, replacement_char):
+    return input_string.replace(character_to_replace, replacement_char)
+
+
+def cleanhtml(raw_html):
+    raw_html = re.sub(r"\*\n", "* ", raw_html)
+    raw_html = re.sub(r"\d{2,3}\s\n", "", raw_html)
+
+    raw_html = re.sub(r"(\d\.)\s\n", r"\1 ", raw_html)
+    raw_html = re.sub(r"\so\s", "* ", raw_html)
+    raw_html = raw_html.replace(
+        "4. Possible side effects \n ", "## Possible side effects\n"
+    )
+    raw_html = raw_html.replace("\n \n5. How to store ", " \n## How to store ")
+    raw_html = raw_html.replace(
+        "\n \n6. Contents of the pack and other information",
+        " \n## Contents of the pack and other information",
+    )
+    raw_html = raw_html.replace("\n \n3. How to take ", " \n## How to take ")
+    raw_html = raw_html.replace(
+        "\n \n2. What you need to know before you take ",
+        " \n## What you need to know before you take ",
+    )
+    raw_html = raw_html.replace("\n \n1. What ", " \n## What ")
+    return raw_html
+
+
+def parse_html(html_content):
+    new_html_content = []
+    endidx = -1
+    pasr = html_content.split("\n")
+    for idx, line in enumerate(pasr):
+        line = replace_unicode_character(line, chr(61607) + " ", "*")
+        new_html_content.append(line)
+        if "B. PACKAGE LEAFLET" or "Package Leaflet (PIL)" in line:  # ema and UK
+            print(line)
+            startidx = idx
+        if (
+            "Detailed information on this medicine is available on the European Medicines Agency web site: "
+            in line
+        ):
+            print(line)
+            endidx = idx + 5
+            break
+    print(startidx, endidx)
+    return "\n".join(new_html_content[startidx:endidx])
+
+
+doc = fitz.open(pdf_path)
+
+# Initialize an empty string to store HTML content
+html_content = ""
+
+# Loop through each page in the PDF and extract text as HTML
+for page in doc:
+    html_content += page.get_text()
+
+
+# Close the PDF document
+doc.close()
+
+
+html_content = parse_html(html_content)
+
+html_content = cleanhtml(html_content)
+# Save the extracted HTML to a file
+with open(html_file_path, "w") as file:
+    file.write(html_content)

ePICreator/pdf-to-html/test-pdf-to-html-es.py

@@ -0,0 +1,78 @@
+import fitz  # PyMuPDF
+import re
+
+
+# Define the path to the PDF file
+pdf_path = "../source-data/epi/xenical-epar-product-information_es.pdf"
+html_file_path = "../source-data/epi/xenical-epar-product-information_es.md"
+
+
+# Open the PDF file
+def replace_unicode_character(input_string, character_to_replace, replacement_char):
+    return input_string.replace(character_to_replace, replacement_char)
+
+
+def cleanhtml(raw_html):
+    raw_html = re.sub(r"\*\n", "* ", raw_html)
+    raw_html = re.sub(r"\d{2,3}\s\n", "", raw_html)
+
+    raw_html = re.sub(r"(\d\.)\s\n", r"\1 ", raw_html)
+    # raw_html = re.sub(r"\so\s", "* ", raw_html)
+    raw_html = raw_html.replace(
+        "4. Possible side effects \n ", "## Possible side effects\n"
+    )
+    raw_html = raw_html.replace("\n \n5. How to store ", " \n## How to store ")
+    raw_html = raw_html.replace(
+        "\n \n6. Contents of the pack and other information",
+        " \n## Contents of the pack and other information",
+    )
+    raw_html = raw_html.replace("\n \n3. How to take ", " \n## How to take ")
+    raw_html = raw_html.replace(
+        "\n \n2. What you need to know before you take ",
+        " \n## What you need to know before you take ",
+    )
+    raw_html = raw_html.replace("\n \n1. What ", " \n## What ")
+    return raw_html
+
+
+def parse_html(html_content):
+    new_html_content = []
+    endidx = -1
+    pasr = html_content.split("\n")
+    for idx, line in enumerate(pasr):
+        line = replace_unicode_character(line, "• ", "*")
+        new_html_content.append(line)
+        if "B. PROSPECTO" in line:  # ema and UK
+            print(line)
+            startidx = idx
+        if (
+            "La información detallada de este medicamento está disponible en la página web de la Agencia Europea de Medicamentos:"
+            in line
+        ):
+            print(line)
+            endidx = idx + 5
+            break
+    print(startidx, endidx)
+    return "\n".join(new_html_content[startidx:endidx])
+
+
+doc = fitz.open(pdf_path)
+
+# Initialize an empty string to store HTML content
+html_content = ""
+
+# Loop through each page in the PDF and extract text as HTML
+for page in doc:
+    html_content += page.get_text()
+
+
+# Close the PDF document
+doc.close()
+
+
+html_content = parse_html(html_content)
+
+html_content = cleanhtml(html_content)
+# Save the extracted HTML to a file
+with open(html_file_path, "w") as file:
+    file.write(html_content)

ePICreator/templates/Bundle.fsh

@@ -12,7 +12,7 @@ RuleSet: {{data["dictionary"]["MajorName"] | lower | regex_replace('[^A-Za-z0-9]
 {%- for refs in value %} 
 
 
-{% if key != "Composition" and key !="Bundle" -%}
+{% if key != "Composition" and key !="Bundle" and key !="List" -%}
 // {{key}}
 {% if "Substance" not in key  -%}
 
@@ -38,8 +38,21 @@ Title: "ePI document Bundle for {{data["dictionary"]["productname"]}} Package Le
 Description: "ePI document Bundle for {{data["dictionary"]["productname"]}} Package Leaflet for language {{row["language"]}}"
 Usage: #example
 
-{% if row["identifier_value"]!="nan"  %}
+{% set ns = namespace() %}
+{% set ns.one =row["language"] %}
+{% set ns.two = data["dictionary"]["productname"]| regex_replace('[^A-Za-z0-9]+', '') %}
+{% set ns.name_to_has= ns.one ~ ns.two   %}
 
+
+
+{% if row["identifier_value"]=="nan"  %}
+* identifier[+].system = "{{row['identifier_system']}}" 
+* identifier.value = "{{ns.name_to_has| create_hash_id}}"
+
+{% elif  row["identifier_value"]=="xx"  %}
+* identifier[+].system = "{{row['identifier_system']}}" 
+* identifier.value = "{{ns.name_to_has| create_hash_id}}"
+{% else %}
 * identifier.system = "{{row['identifier_system']}}" 
 * identifier.value = "{{row["identifier_value"]|trim}}"
 {% endif %}

ePICreator/templates/Composition.fsh

@@ -2,7 +2,29 @@
 {% if row["skip"] not in ['y', 'Y', 'x', 'X'] %}
 
 {% set ns = namespace() %}
+{% if row["language"] == "es"%}
+{% set ns.title = "B. PROSPECTO" %}
+{% set ns.user = "PROSPECTO: INFORMACIÓN PARA EL USUARIO" %}
+{% set ns.leaflet = "Contenido del prospecto" %}
+{% set ns.h1 = "1. Qué es "~row['name']~" y para qué se utiliza"%}
+
+{% set ns.h2 = "2. Qué necesita saber antes de empezar a tomar " ~row['name'] %}
+{% set ns.h3 = "3. Cómo tomar "~row['name'] %}
+{% set ns.h4 = "4. Posibles efectos adversos" %}
+{% set ns.h5 = "5. CONSERVACIÓN DE "~row['name'] %}
+{% set ns.h6 = "6. Contenido del envase e información adicional" %}
 
+{% else %}
+{% set ns.title = "B. Package Leaflet" %}
+{% set ns.user = "Package leaflet: Information for the user" %}
+{% set ns.leaflet = "What is in this leaflet" %}
+{% set ns.h1 = "1. What "~row['name']~" is and what it is used for" %}
+{% set ns.h2 = "2. What you need to know before you take "~row['name'] %}
+{% set ns.h3 = "3. How to take "~row['name'] %}
+{% set ns.h4 = "4. Possible side effects" %}
+{% set ns.h5 = "5. How to store "~row['name'] %}
+{% set ns.h6 = "6. Contents of the pack and other information" %}
+{% endif %}
 
 Instance: composition-{{row["language"]}}-{{data["dictionary"]["productname"]| regex_replace('[^A-Za-z0-9]+', '')| create_hash_id}}
 InstanceOf: CompositionUvEpi
@@ -13,7 +35,6 @@ Usage: #example
 * identifier.system = "{{row['identifier_system']}}"
 
 {% if row["identifier"]|string == "nan" %}
-{% set ns = namespace() %}
 {% set ns.one = "Composition" %}
 {% set ns.two = data["dictionary"]["productname"]| regex_replace('[^A-Za-z0-9]+', '') %}
 {% set ns.name_to_has= ns.one ~ ns.two   %}
@@ -58,9 +79,9 @@ Usage: #example
 
 
 * section[+].
-  * title = "B. Package Leaflet"
+  * title = "{{ns.title}}"
   * code = https://spor.ema.europa.eu/rmswi/#100000155538
-  * code.text = "B. PACKAGE LEAFLET"
+  * code.text = "{{ns.title}}"
   * text.status = #additional
 {% if row["package_leaflet"]|string == "nan" %}
 
@@ -76,9 +97,9 @@ Usage: #example
 
 
 * section[=].section[+]
-  * title = "Package leaflet: Information for the user"
+  * title = "{{ns.user}}"
   * code = https://spor.ema.europa.eu/rmswi/#100000155538
-  * code.text = "Package leaflet: Information for the user"
+  * code.text = "{{ns.user}}"
   * text.status = #additional
 {% if row["information_user"]|string == "nan" %}
 
@@ -94,9 +115,9 @@ Usage: #example
 
 
 * section[=].section[+]
-  * title = "What is in this leaflet"
+  * title = "{{ns.leaflet}}"
   * code = https://spor.ema.europa.eu/rmswi/#100000155538
-  * code.text = "What is in this leaflet"
+  * code.text = "{{ns.leaflet}}"
   * text.status = #additional
 {% if row["what_in_leaflet"]|string == "nan" %}
 
@@ -111,9 +132,9 @@ Usage: #example
 
 
 * section[=].section[+]
-  * title = "1. What {{row['name']}} is and what it is used for"
+  * title =  "{{ns.h1}}"
   * code = https://spor.ema.europa.eu/rmswi/#100000155538
-  * code.text = "1. What {{row['name']}} is and what it is used for"
+  * code.text =  "{{ns.h1}}"
   * text.status = #additional
 {% if row["what_product_is"]|string == "nan" %}
 
@@ -130,9 +151,9 @@ Usage: #example
 
 
 * section[=].section[+]
-  * title = "2. What you need to know before you take {{row['name']}}"
+  * title = "{{ns.h2}}"
   * code = https://spor.ema.europa.eu/rmswi/#100000155538
-  * code.text = "2. What you need to know before you take {{row['name']}}"
+  * code.text = "{{ns.h2}}"
   * text.status = #additional
 {% if row["before_take"]|string == "nan" %}
 
@@ -146,9 +167,9 @@ Usage: #example
 {%- endif %}   
 
 * section[=].section[+]
-  * title = "3. How to take {{row['name']}}"
+  * title =  "{{ns.h3}}"
   * code = https://spor.ema.europa.eu/rmswi/#100000155538
-  * code.text = "3. How to take {{row['name']}}"
+  * code.text = "{{ns.h3}}"
   * text.status = #additional
 {% if row["how_to_take"]|string == "nan" %}
 
@@ -163,9 +184,9 @@ Usage: #example
 
 
 * section[=].section[+]
-  * title = "4. Possible side effects"
+  * title = "{{ns.h4}}"
   * code = https://spor.ema.europa.eu/rmswi/#100000155538
-  * code.text = "4. Possible side effects"
+  * code.text = "{{ns.h4}}"
   * text.status = #additional
 {% if row["side_effects"]|string == "nan" %}
 
@@ -179,9 +200,9 @@ Usage: #example
 {%- endif %}      
 
 * section[=].section[+]
-  * title = "5. How to store {{row['name']}}"
+  * title = "{{ns.h5}}"
   * code = https://spor.ema.europa.eu/rmswi/#100000155538
-  * code.text = "5. How to store {{row['name']}}"
+  * code.text = "{{ns.h5}}"
   * text.status = #additional
 {% if row["how_to_store"]|string == "nan" %}
 
@@ -196,9 +217,9 @@ Usage: #example
 
 
 * section[=].section[+]
-  * title = "6. Contents of the pack and other information"
+  * title = "{{ns.h6}}"
   * code = https://spor.ema.europa.eu/rmswi/#100000155538
-  * code.text = "6. Contents of the pack and other information"
+  * code.text = "{{ns.h6}}"
   * text.status = #additional
 {% if row["other_info"]|string == "nan" %}
 

ePICreator/templates/List.fsh

@@ -1,4 +1,4 @@
-
+{% if data["data"]|length> 1%}
 
 
 
@@ -53,3 +53,4 @@ Description: "List of {{data["dictionary"]["MajorName"]}} Package Leaflets"
 {%- endif %}
 {%- endfor %}
 
+{%- endif %}

ePICreator/templates/RegulatedAuthorization.fsh

@@ -21,6 +21,9 @@ Usage: #example
 * subject = Reference({{data["references"]["MedicinalProductDefinition"][0][0]}})
 {% elif row["reference"] == "PackagedProduct"%}
 * subject = Reference({{data["references"]["PackagedProductDefinition"][index][0]}})
+{% else %}
+* subject = Reference({{data["references"]["MedicinalProductDefinition"][0][0]}})
+
 {% endif %}
 
 {% endif %}

input/fsh/examples/List.fsh

@@ -17,8 +17,6 @@ Description: "List of enbrel smpc  Package Leaflets"
 
 * code = $example-pi-list-types#00000021213 "ePI Master List"
 
-
-
 * subject = Reference(mp25bbfa948f4a0b224f9baa1fe481efa8)
 * subject.extension[0].url = "http://ema.europa.eu/fhir/extension/medicine-name"
 * subject.extension[=].valueCoding = $100000000005#Enbrel "Enbrel"
@@ -51,9 +49,6 @@ Description: "List of enbrel smpc  Package Leaflets"
 
 
 
-
-
-
 Instance: listDovato
 InstanceOf: List
 Usage: #example